Antoni B. Chan

Yaowu Fan, Jia Wan, Tao Han et al.

Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera datasets with limited scene coverage, making them inadequate for crowd analysis in large-scale scenes. To bridge this gap, we introduce MovingDroneCrowd++, the largest video-level dataset dedicated to dense crowd counting and tracking with fast-moving drones, captured under diverse flight altitudes, camera angles, and illumination conditions. Existing methods, however, still fail to achieve satisfactory video individual counting or tracking performance under these challenging aerial conditions. To this end, we propose GD3A (Global Density map Decomposition via group-wise Descriptor Association), a video individual counting method that first establishes pixel-level correspondences between pedestrian descriptors across frames via optimal transport with an adaptive dustbin score. Then, group-wise association is adopted to guide the decomposition of the global density map into shared, inflow, and outflow density maps. We further introduce a pedestrian tracking method, DVTrack (Descriptor Voting Track), which converts descriptor-level matching into instance-level association through descriptor voting. Our methods rely on the association results of group-wise multiple descriptors for each pedestrian rather than a single vector. Since intra-group matching errors do not affect the final counting and tracking results, our methods are more robust in dense crowds and challenging aerial conditions. Experiments show that our methods achieve substantial gains in both crowd counting and tracking on moving-drone videos with dense crowds and complex motions, reducing counting error by 47.4% and improving tracking accuracy by 64.6%. Code, dataset, and pretrained models are available at https://github.com/fyw1999/MovingDroneCrowd.

Yan Xia, Qiangqiang Wu, Wei Li et al.

Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking. However, it is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. In this paper, we address this issue by explicitly leveraging temporal motion cues and propose DMT, a Detector-free Motion-prediction-based 3D Tracking network that completely removes the usage of complicated 3D detectors and is lighter, faster, and more accurate than previous trackers. Specifically, the motion prediction module is first introduced to estimate a potential target center of the current frame in a point-cloud-free manner. Then, an explicit voting module is proposed to directly regress the 3D box from the estimated target center. Extensive experiments on KITTI and NuScenes datasets demonstrate that our DMT can still achieve better performance (~10% improvement over the NuScenes dataset) and a faster tracking speed (i.e., 72 FPS) than state-of-the-art approaches without applying any complicated 3D detectors. Our code is released at \url{https://github.com/jimmy-dq/DMT}

Ziquan Liu, Yi Xu, Xiangyang Ji et al.

Recent years have seen the ever-increasing importance of pre-trained models and their downstream training in deep learning research and applications. At the same time, the defense for adversarial examples has been mainly investigated in the context of training from random initialization on simple classification tasks. To better exploit the potential of pre-trained models in adversarial robustness, this paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. Existing research has shown that since the robust pre-trained model has already learned a robust feature extractor, the crucial question is how to maintain the robustness in the pre-trained model when learning the downstream task. We study the model-based and data-based approaches for this goal and find that the two common approaches cannot achieve the objective of improving both generalization and adversarial robustness. Thus, we propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework, which consists of two neural networks where one of them keeps the population means and variances of pre-training data in the batch normalization layers. Besides the robust information transfer, TWINS increases the effective learning rate without hurting the training stability since the relationship between a weight norm and its gradient norm in standard batch normalization layer is broken, resulting in a faster escape from the sub-optimal initialization and alleviating the robust overfitting. Finally, TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness. Our code is available at https://github.com/ziquanliu/CVPR2023-TWINS.

Xueying Zhan, Qingzhong Wang, Kuan-hao Huang et al.

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and training. Therefore, Deep Active Learning (DAL) has risen as a feasible solution for maximizing model performance under a limited labeling cost/budget in recent years. Although abundant methods of DAL have been developed and various literature reviews conducted, the performance evaluation of DAL methods under fair comparison settings is not yet available. Our work intends to fill this gap. In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods. We survey and categorize DAL-related works and construct comparative experiments across frequently used datasets and DAL algorithms. Additionally, we explore some factors (e.g., batch size, number of epochs in the training process) that influence the efficacy of DAL, which provides better references for researchers to design their DAL experiments or carry out DAL-related applications.

Qi Zhang, Wei Lin, Antoni B. Chan

Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve counting performance for occluded people or those in low resolution. However, the current multi-view paradigm trains and tests on the same single scene and camera-views, which limits its practical application. In this paper, we propose a cross-view cross-scene (CVCS) multi-view crowd counting paradigm, where the training and testing occur on different scenes with arbitrary camera layouts. To dynamically handle the challenge of optimal view fusion under scene and camera layout change and non-correspondence noise due to camera calibration errors or erroneous features, we propose a CVCS model that attentively selects and fuses multiple views together using camera layout geometry, and a noise view regularization method to train the model to handle non-correspondence errors. We also generate a large synthetic multi-camera crowd counting dataset with a large number of scenes and camera views to capture many possible variations, which avoids the difficulty of collecting and annotating such a large real dataset. We then test our trained CVCS model on real multi-view counting datasets, by using unsupervised domain transfer. The proposed CVCS model trained on synthetic data outperforms the same model trained only on real data, and achieves promising performance compared to fully supervised methods that train and test on the same single scene.

Qiangqiang Wu, Tianyu Yang, Ziquan Liu et al.

This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracking (VOT) and video object segmentation (VOS), self-supervised visual correspondence learning, dense tracking tasks including optical flow estimation and long-term point tracking, and 3D point cloud tracking. Specifically, our work explores to provide a general representation to boost the temporal matching ability in various downstream tracking tasks. To achieve this, we firstly find that a simple extension of MAE, which randomly masks out frame patches in videos and reconstruct the frame pixels, heavily relies on spatial cues while ignoring temporal relations for frame reconstruction, thus leading to sub-optimal temporal matching representations. To alleviate this, we propose DropMAE, which adaptively performs spatial-attention dropout in the frame reconstruction to facilitate temporal correspondence learning in videos. We obtain several important findings with DropMAE: 1) DropMAE is a strong and efficient temporal matching learner, which achieves better fine-tuning results on matching-based tasks than the ImageNet-based MAE with 2x faster pre-training speed. 2) DropMAE is effective for different tracking tasks, i.e., object-level matching tasks including VOT and VOS, dense tracking tasks including optical flow estimation and tracking any point (TAP), and even 3D tracking in the different modality of point cloud data. Since none exists, we build ViT-based trackers for different downstream tracking tasks, and our pre-trained DropMAE model can be directly loaded in these ViT-based trackers for fine-tuning without further modifications. Experiments on 6 downstream tracking tasks demonstrate the effectiveness of DropMAE as a general pre-trained representation for diverse tracking tasks.

Xin Huang, Antoni B. Chan

Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet comparing such explanations remains challenging. Existing soft-perturbation faithfulness metrics, such as Soft-NC and Soft-NS, can conflate attribution quality with the number of words retained during perturbation: attribution methods with larger average scores may keep more words and therefore obtain inflated scores. To address this issue, we propose $π$-Soft-NC and $π$-Soft-NS, an evaluation framework that compares attribution methods under the same expected retaining probability, thus controlling the number of retained words. We further introduce Grad-ELLM, a gradient-based attribution method tailored to autoregressive decoder-only LLMs, which combines gradient-derived channel importance with attention-derived token importance at each decoding step. Experiments on classification and open-generation tasks with Llama and Mistral show that Grad-ELLM achieves strong comprehensiveness-oriented faithfulness under $π$-Soft-NC, while there is no dominant method under $π$-Soft-NS. Our evaluation metric serves as a rigorous framework to compare XAI methods for LLMs, which will support progress in the field.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Recent image captioning models are achieving impressive results based on popular metrics, i.e., BLEU, CIDEr, and SPICE. However, focusing on the most popular metrics that only consider the overlap between the generated captions and human annotation could result in using common words and phrases, which lacks distinctiveness, i.e., many similar images have the same caption. In this paper, we aim to improve the distinctiveness of image captions via comparing and reweighting with a set of similar images. First, we propose a distinctiveness metric -- between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images. Our metric reveals that the human annotations of each image in the MSCOCO dataset are not equivalent based on distinctiveness; however, previous works normally treat the human annotations equally during training, which could be a reason for generating less distinctive captions. In contrast, we reweight each ground-truth caption according to its distinctiveness during training. We further integrate a long-tailed weight strategy to highlight the rare words that contain more information, and captions from the similar image set are sampled as negative examples to encourage the generated sentence to be unique. Finally, extensive experiments are conducted, showing that our proposed approach significantly improves both distinctiveness (as measured by CIDErBtw and retrieval metrics) and accuracy (e.g., as measured by CIDEr) for a wide variety of image captioning baselines. These results are further confirmed through a user study.

Ziquan Liu, Yi Xu, Yuanhong Xu et al.

The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the robustness to distribution shift from the algorithmic perspective, i.e., designing better training algorithms to help the generalization in shifted test distributions. This paper studies the distribution shift problem from the perspective of pre-training and data augmentation, two important factors in the practice of deep learning that have not been systematically investigated by existing work. By evaluating seven pre-trained models, including ResNets and ViT's with self-supervision and supervision mode, on five important distribution-shift datasets, from WILDS and DomainBed benchmarks, with five different learning algorithms, we provide the first comprehensive empirical study focusing on pre-training and data augmentation. With our empirical result obtained from 1,330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e.g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts. In summary, our empirical study provides a comprehensive baseline for a wide range of pre-training models fine-tuned with data augmentation, which potentially inspires research exploiting the power of pre-training and data augmentation in the future of distribution shift study.

Yuanzhi Wang, Yong Li, Xiaoya Zhang et al.

Large-scale text-to-image (T2I) diffusion models have been extended for text-guided video editing, yielding impressive zero-shot video editing performance. Nonetheless, the generated videos usually show spatial irregularities and temporal inconsistencies as the temporal characteristics of videos have not been faithfully modeled. In this paper, we propose an elegant yet effective Temporal-Consistent Video Editing (TCVE) method to mitigate the temporal inconsistency challenge for robust text-guided video editing. In addition to the utilization of a pretrained T2I 2D Unet for spatial content manipulation, we establish a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences. Furthermore, to establish coherence and interrelation between the spatial-focused and temporal-focused components, a cohesive spatial-temporal modeling unit is formulated. This unit effectively interconnects the temporal Unet with the pretrained 2D Unet, thereby enhancing the temporal consistency of the generated videos while preserving the capacity for video content manipulation. Quantitative experimental results and visualization results demonstrate that TCVE achieves state-of-the-art performance in both video temporal consistency and video editing capability, surpassing existing benchmarks in the field.

Chenyang Zhao, Antoni B. Chan

We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate feature maps, ODAM produces heat maps that show the influence of regions on the detector's decision for each predicted attribute. Compared to previous works classification activation maps (CAM), ODAM generates instance-specific explanations rather than class-specific ones. We show that ODAM is applicable to both one-stage detectors and two-stage detectors with different types of detector backbones and heads, and produces higher-quality visual explanations than the state-of-the-art both effectively and efficiently. We next propose a training scheme, Odam-Train, to improve the explanation ability on object discrimination of the detector through encouraging consistency between explanations for detections on the same object, and distinct explanations for detections on different objects. Based on the heat maps produced by ODAM with Odam-Train, we propose Odam-NMS, which considers the information of the model's explanation for each prediction to distinguish the duplicate detected objects. We present a detailed analysis of the visualized explanations of detectors and carry out extensive experiments to validate the effectiveness of the proposed ODAM.

Ziquan Liu, Antoni B. Chan

The adversarial vulnerability of deep neural networks (DNNs) has been actively investigated in the past several years. This paper investigates the scale-variant property of cross-entropy loss, which is the most commonly used loss function in classification tasks, and its impact on the effective margin and adversarial robustness of deep neural networks. Since the loss function is not invariant to logit scaling, increasing the effective weight norm will make the loss approach zero and its gradient vanish while the effective margin is not adequately maximized. On typical DNNs, we demonstrate that, if not properly regularized, the standard training does not learn large effective margins and leads to adversarial vulnerability. To maximize the effective margins and learn a robust DNN, we propose to regularize the effective weight norm during training. Our empirical study on feedforward DNNs demonstrates that the proposed effective margin regularization (EMR) learns large effective margins and boosts the adversarial robustness in both standard and adversarial training. On large-scale models, we show that EMR outperforms basic adversarial training, TRADES and two regularization baselines with substantial improvement. Moreover, when combined with several strong adversarial defense methods (MART and MAIL), our EMR further boosts the robustness.

Xueying Zhan, Zeyu Dai, Qingzhong Wang et al.

Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However, existing AL sampling strategies might not work well in out-of-distribution (OOD) data scenarios, where the unlabeled data pool contains some data samples that do not belong to the classes of the target task. Achieving good AL performance under OOD data scenarios is a challenging task due to the natural conflict between AL sampling strategies and OOD sample detection. AL selects data that are hard to be classified by the current basic classifier (e.g., samples whose predicted class probabilities have high entropy), while OOD samples tend to have more uniform predicted class probabilities (i.e., high entropy) than in-distribution (ID) data. In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool. We cast the AL sampling task as a multi-objective optimization problem, and thus we utilize Pareto optimization based on two conflicting objectives: (1) the normal AL data sampling scheme (e.g., maximum entropy), and (2) the confidence of not being an OOD sample. Experimental results show its effectiveness on both classical Machine Learning (ML) and Deep Learning (DL) tasks.

Xu Cui, Xinyan Liu, Chen Yang et al.

Fine-grained semantic segmentation of transmission-corridor point clouds is fundamental for intelligent power-line inspection. However, current progress is limited by realistic data scarcity and the difficulty of modeling global corridor structure and local geometric details in long, heterogeneous scenes. Existing public datasets usually provide only a few coarse categories or short cropped scenes which overlook long-range structural dependencies, severe long-tail distributions, and subtle distinctions among safety-critical components. As a result, current methods are difficult to evaluate under realistic inspection settings, and their ability to preserve and integrate complementary global and local cues remains unclear. To address the above challenges, we introduce TowerDataset, a heterogeneous benchmark for transmission-corridor segmentation. TowerDataset contains 661 real-world scenes and about 2.466 billion points. It preserves long corridor extents, defines a fine-grained 22-class taxonomy, and provides standardized splits and evaluation protocols. In addition, we present a global-local fusion framework which preserves and fuses whole-scene and local-detail information. A whole-scene branch with NoCrop training and prototypical contrastive learning captures long-range topology and contextual dependencies. A block-wise local branch retains fine geometric structures. Both predictions are then fused and refined by geometric validation. This design allows the model to exploit both global relationships and local shape details when recognizing rare and confusing components. Experiments on TowerDataset and two public benchmarks demonstrate the challenge of the proposed benchmark and the robustness of our framework in real, complex, and heterogeneous transmission-corridor scenes. The dataset will be released soon at https://huggingface.co/datasets/tccx18/Towerdataset/tree/main.

Zelin Zheng, Xinyan Liu, Ruixin Li et al.

Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle numerics and inconsistent boundaries. To address this, we propose Foresee-to-Ground (F2G), a framework that reformulates VTG as a verifiable Identify-then-Measure problem. F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning: it learns boundary-sensitive temporal representations to build a video-wide evidence pool of candidate event segments, and exposes these segments to the LLM as citable evidence units that bind boundary prediction to explicit event hypotheses. By decoupling event identification from precise boundary measurement, F2G stabilizes grounding and makes predictions verifiable. Extensive experiments demonstrate that F2G consistently improves grounding accuracy across diverse benchmarks, transfers robustly across different Video-LLM backbones, and preserves general video understanding capabilities.

Jiyang Huang, Hongru Cheng, Wei Lin et al.

Semi-supervised crowd analysis is a prominent area of research, as unlabeled data are typically abundant and inexpensive to obtain. However, traditional point-based annotations constrain performance because individual regions are inherently ambiguous, and consequently, learning fine-grained structural semantics from sparse anno tations remains an unresolved challenge. In this paper, we first propose an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM), based on our Nearest Neighbor Exclusion Circle (NNEC) constraint, to generate mask supervision for current datasets. With the aim of segmenting individuals in dense scenes, we then propose Exclusivity-Guided Mask Learning (XMask), which enforces spatial separation through a discriminative mask objective. Gaussian smoothing and a differentiable center sampling strategy are utilized to improve feature continuity and training stability. Building on XMask, we present a semi-supervised crowd counting framework that uses instance mask priors as pseudo-labels, which contain richer shape information than traditional point cues. Extensive experiments on the ShanghaiTech A, UCF-QNRF, and JHU++ datasets (using 5%, 10%, and 40% labeled data) verify that our end-to-end model achieves state-of-the-art semi-supervised segmentation and counting performance, effectively bridging the gap between counting and instance segmentation within a unified framework.

Qi Zhang, Kaiyi Zhang, Antoni B. Chan et al.

Multi-view crowd localization predicts the ground locations of all people in the scene. Typical methods usually estimate the crowd density maps on the ground plane first, and then obtain the crowd locations. However, the performance of existing methods is limited by the ambiguity of the density maps in crowded areas, where local peaks can be smoothed away. To mitigate the weakness of density map supervision, optimal transport-based point supervision methods have been proposed in the single-image crowd localization tasks, but have not been explored for multi-view crowd localization yet. Thus, in this paper, we propose a novel Mahalanobis distance-based multi-view optimal transport (M-MVOT) loss specifically designed for multi-view crowd localization. First, we replace the Euclidean-based transport cost with the Mahalanobis distance, which defines elliptical iso-contours in the cost function whose long-axis and short-axis directions are guided by the view ray direction. Second, the object-to-camera distance in each view is used to adjust the optimal transport cost of each location further, where the wrong predictions far away from the camera are more heavily penalized. Finally, we propose a strategy to consider all the input camera views in the model loss (M-MVOT) by computing the optimal transport cost for each ground-truth point based on its closest camera. Experiments demonstrate the advantage of the proposed method over density map-based or common Euclidean distance-based optimal transport loss on several multi-view crowd localization datasets. Project page: https://vcc.tech/research/2024/MVOT.

Chenyang Zhao, Kun Wang, Janet H. Hsiao et al.

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a Gradient-based visual and textual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Furthermore, a series of analysis are conducted based on our visual and textual explanation results, from which we explore the working mechanism of image-text matching, the strengths and limitations in attribution identification of CLIP, and the relationship between the concreteness/abstractness of a word and its usage in CLIP. Finally, based on the ability of explanation map that indicates text-specific saliency region of input image, we also propose an application with Grad-ECLIP, which is adopted to boost the fine-grained alignment in the CLIP fine-tuning. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.

Qi Zhang, Jixuan Chen, Kaiyi Zhang et al.

Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene. Recent research works mainly rely on CNNs-based multi-view crowd tracking architectures, and most of them are evaluated and compared on relatively small datasets, such as Wildtrack and MultiviewX. Since these two datasets are collected in small scenes and only contain tens of frames in the evaluation stage, it is difficult for the current methods to be applied to real-world applications where scene size and occlusion are more complicated. In this paper, we propose a Transformer-based multi-view crowd tracking model, \textit{MVTrackTrans}, which adopts interactions between camera views and the ground plane for enhanced multi-view tracking performance. Besides, for better evaluation, we collect and label two large real-world multi-view tracking datasets, MVCrowdTrack and CityTrack, which contain a much larger scene size over a longer time period. Compared with existing methods on the two large and new datasets, the proposed MVTrackTrans model achieves better performance, demonstrating the advantages of the model design in dealing with large scenes. We believe the proposed datasets and model will push the frontiers of the task to more practical scenarios, and the datasets and code are available at: https://github.com/zqyq/MVTrackTrans.

Qiangqiang Wu, Tianyu Yang, Bo Fang et al.

Tracking Any Point (TAP) has emerged as a fundamental tool for video understanding. Current approaches adapt Vision Foundation Models (VFMs) like DINOv2 via offline finetuning or test-time optimization. However, these VFMs rely on static image pre-training, which is inherently sub-optimal for capturing dense temporal correspondence in videos. To address this, we propose Mask-to-Point (M2P) learning, which leverages rich video object segmentation (VOS) mask annotations to improve VFMs for dense point tracking. Our M2P introduces three new mask-based constraints for weakly-supervised representation learning. First, we propose a local structure consistency loss, which leverages Procrustes analysis to model the cohesive motion of points lying within a local structure, achieving more reliable point-to-point matching learning. Second, we propose a mask label consistency (MLC) loss, which enforces that sampled foreground points strictly match foreground regions across frames. The proposed MLC loss can be regarded as a regularization, which stabilizes training and prevents convergence to trivial solutions. Finally, mask boundary constrain is applied to explicitly supervise boundary points. We show that our weaklysupervised M2P models significantly outperform baseline VFMs with efficient training by using only 3.6K VOS training videos. Notably, M2P achieves 12.8% and 14.6% performance gains over DINOv2-B/14 and DINOv3-B/16 on the TAP-Vid-DAVIS benchmark, respectively. Moreover, the proposed M2P models are used as pre-trained backbones for both test-time optimized and offline fine-tuned TAP tasks, demonstrating its potential to serve as general pre-trained models for point tracking. Code will be made publicly available upon acceptance.

Wei Lin, Chenyang Zhao, Antoni B. Chan

Point detection has been developed to locate pedestrians in crowded scenes by training a counter through a point-to-point (P2P) supervision scheme. Despite its excellent localization and counting performance, training a point-based counter still faces challenges concerning annotation labor: hundreds to thousands of points are required to annotate a single sample capturing a dense crowd. In this paper, we integrate point-based methods into a semi-supervised counting framework based on pseudo-labeling, enabling the training of a counter with only a few annotated samples supplemented by a large volume of pseudo-labeled data. However, during implementation, the training encounters issues as the confidence for pseudo-labels fails to be propagated to background pixels via the P2P. To tackle this challenge, we devise a point-specific activation map (PSAM) to visually interpret the phenomena occurring during the ill-posed training. Observations from the PSAM suggest that the feature map is excessively activated by the loss for unlabeled data, causing the decoder to misinterpret these over-activations as pedestrians. To mitigate this issue, we propose a point-to-region (P2R) scheme to substitute P2P, which segments out local regions rather than detects a point corresponding to a pedestrian for supervision. Consequently, pixels in the local region can share the same confidence with the corresponding pseudo points. Experimental results in both semi-supervised counting and unsupervised domain adaptation highlight the advantages of our method, illustrating P2R can resolve issues identified in PSAM. The code is available at https://github.com/Elin24/P2RLoss.

Qi Zhang, Yunfei Gong, Zhidan Xie et al.

Multi-view crowd counting has been proposed to deal with the severe occlusion issue of crowd counting in large and wide scenes. However, due to the difficulty of collecting and annotating multi-view images, the datasets for multi-view counting have a limited number of multi-view frames and scenes. To solve the problem of limited data, one approach is to collect synthetic data to bypass the annotating step, while another is to propose semi- or weakly-supervised or unsupervised methods that demand less multi-view data. In this paper, we propose two semi-supervised multi-view crowd counting frameworks by ranking the multi-view fusion models of different numbers of input views, in terms of the model predictions or the model uncertainties. Specifically, for the first method (vanilla model), we rank the multi-view fusion models' prediction results of different numbers of camera-view inputs, namely, the model's predictions with fewer camera views shall not be larger than the predictions with more camera views. For the second method, we rank the estimated model uncertainties of the multi-view fusion models with a variable number of view inputs, guided by the multi-view fusion models' prediction errors, namely, the model uncertainties with more camera views shall not be larger than those with fewer camera views. These constraints are introduced into the model training in a semi-supervised fashion for multi-view counting with limited labeled data. The experiments demonstrate the advantages of the proposed multi-view model ranking methods compared with other semi-supervised counting methods.

Bo Fang, Yuxin Song, Qiangqiang Wu et al.

Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video tasks, such strategies frequently underutilize rich visual information, leading to potential shortcut learning and increased susceptibility to hallucination. To foster a more robust, visual-centric video understanding, we start by introducing a novel self-supervised reinforcement learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline, in which positive rewards are assigned for correctly solving pretext tasks on transformed visual inputs, which makes the model to non-trivially process the visual information. Building on the effectiveness of Pretext-GRPO, we further propose the ViSS-R1 framework, which streamlines and integrates pretext-task-based self-supervised learning directly into the MLLM's R1 post-training paradigm. Instead of relying solely on sparse visual cues, our framework compels models to reason about transformed visual input by simultaneously processing both pretext questions (concerning transformations) and true user queries. This necessitates identifying the applied transformation and reconstructing the original video to formulate accurate final answers. Comprehensive evaluations on six widely-used video reasoning and understanding benchmarks demonstrate the effectiveness and superiority of our Pretext-GRPO and ViSS-R1 for complex video reasoning. Our codes and models will be publicly available.

Wei Lin, Antoni B. Chan

Existing class-agnostic counting models typically rely on a single type of prompt, e.g., box annotations. This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for concerned objects indicated by various prompt types, such as box, point, and text. To achieve this goal, we begin by converting prompts from different modalities into prompt masks without requiring training. These masks are then integrated into a class-agnostic counting methodology for predicting density maps. Furthermore, we introduce a fixed-point inference along with an associated loss function to improve counting accuracy, all without introducing new parameters. The effectiveness of this method is substantiated both theoretically and experimentally. Additionally, a contrastive training scheme is implemented to mitigate dataset bias inherent in current class-agnostic counting datasets, a strategy whose effectiveness is confirmed by our ablation study. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.

Yuanzhi Wang, Yong Li, Mengyi Liu et al.

Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by proposing a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method. Specially, to align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD) to refocus the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video. In particular, to faithfully preserve the invariant region content with less border artifacts, we propose an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors w.r.t the invariant regions at each denoising timestep and constrain the generated content to be harmonized with the invariant region content. Experimental results verify that ReAtCo consistently improves the controllability of video diffusion editing and achieves superior video editing performance.

Wei Wu, Qingnan Fan, Shuai Qin et al.

Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature. However, such attempts face the pivotal challenge of misalignment between the intended precise editing target regions and the broader area impacted by the guidance in practice. Despite excellent methods leveraging attention mechanisms that have been developed to refine the editing guidance, these approaches necessitate modifications through complex network architecture and are limited to specific editing tasks. In this work, we re-examine the diffusion process and misalignment problem from a frequency perspective, revealing that, due to the power law of natural images and the decaying noise schedule, the denoising network primarily recovers low-frequency image components during the earlier timesteps and thus brings excessive low-frequency signals for editing. Leveraging this insight, we introduce a novel fine-tuning free approach that employs progressive $\textbf{Fre}$qu$\textbf{e}$ncy truncation to refine the guidance of $\textbf{Diff}$usion models for universal editing tasks ($\textbf{FreeDiff}$). Our method achieves comparable results with state-of-the-art methods across a variety of editing tasks and on a diverse set of images, highlighting its potential as a versatile tool in image editing applications.

Ziquan Liu, Yufei Cui, Yan Yan et al.

In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks and reliable uncertainty quantification in decision-making. With extensive research focused on enhancing adversarial robustness through various forms of adversarial training (AT), a notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. To address this gap, this study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks within the adversarial defense community. It is first unveiled that existing CP methods do not produce informative prediction sets under the commonly used $l_{\infty}$-norm bounded attack if the model is not adversarially trained, which underpins the importance of adversarial training for CP. Our paper next demonstrates that the prediction set size (PSS) of CP using adversarially trained models with AT variants is often worse than using standard AT, inspiring us to research into CP-efficient AT for improved PSS. We propose to optimize a Beta-weighting loss with an entropy minimization regularizer during AT to improve CP-efficiency, where the Beta-weighting loss is shown to be an upper bound of PSS at the population level by our theoretical analysis. Moreover, our empirical study on four image classification datasets across three popular AT baselines validates the effectiveness of the proposed Uncertainty-Reducing AT (AT-UR).

Jia Wan, Qiangqiang Wu, Wei Lin et al.

The existing crowd counting models require extensive training data, which is time-consuming to annotate. To tackle this issue, we propose a simple yet effective crowd counting method by utilizing the Segment-Everything-Everywhere Model (SEEM), an adaptation of the Segmentation Anything Model (SAM), to generate pseudo-labels for training crowd counting models. However, our initial investigation reveals that SEEM's performance in dense crowd scenes is limited, primarily due to the omission of many persons in high-density areas. To overcome this limitation, we propose an adaptive resolution SEEM to handle the scale variations, occlusions, and overlapping of people within crowd scenes. Alongside this, we introduce a robust localization method, based on Gaussian Mixture Models, for predicting the head positions in the predicted people masks. Given the mask and point pseudo-labels, we propose a robust loss function, which is designed to exclude uncertain regions based on SEEM's predictions, thereby enhancing the training process of the counting networks. Finally, we propose an iterative method for generating pseudo-labels. This method aims at improving the quality of the segmentation masks by identifying more tiny persons in high-density regions, which are often missed in the first pseudo-labeling stage. Overall, our proposed method achieves the best unsupervised performance in crowd counting, while also being comparable results to some supervised methods. This makes it a highly effective and versatile tool for crowd counting, especially in situations where labeled data is not available.

Bo Fang, Wenhao Wu, Qiangqiang Wu et al.

Audio Descriptions (ADs) aim to provide a narration of a movie in text form, describing non-dialogue-related narratives, such as characters, actions, or scene establishment. Automatic generation of ADs remains challenging due to: i) the domain gap between movie-AD data and existing data used to train vision-language models, and ii) the issue of contextual redundancy arising from highly similar neighboring visual clips in a long movie. In this work, we propose DistinctAD, a novel two-stage framework for generating ADs that emphasize distinctiveness to produce better narratives. To address the domain gap, we introduce a CLIP-AD adaptation strategy that does not require additional AD corpora, enabling more effective alignment between movie and AD modalities at both global and fine-grained levels. In Stage-II, DistinctAD incorporates two key innovations: (i) a Contextual Expectation-Maximization Attention (EMA) module that reduces redundancy by extracting common bases from consecutive video clips, and (ii) an explicit distinctive word prediction loss that filters out repeated words in the context, ensuring the prediction of unique terms specific to the current AD. Comprehensive evaluations on MAD-Eval, CMD-AD, and TV-AD benchmarks demonstrate the superiority of DistinctAD, with the model consistently outperforming baselines, particularly in Recall@k/N, highlighting its effectiveness in producing high-quality, distinctive ADs.

Bo Fang, Wenhao Wu, Qiangqiang Wu et al.

Employing Multimodal Large Language Models (MLLMs) for long video understanding remains a challenging problem due to the dilemma between the substantial number of video frames (i.e., visual tokens) versus the limited context length of language models. Traditional uniform sampling often leads to selection of irrelevant content, while post-training MLLMs on thousands of frames imposes a substantial computational burden. In this paper, we propose threading keyframes with narratives (Nar-KFC), a plug-and-play module to facilitate effective and efficient long video perception. Nar-KFC generally involves two collaborative steps. First, we formulate the keyframe selection process as an integer quadratic programming problem, jointly optimizing query-relevance and frame-diversity. To avoid its computational complexity, a customized greedy search strategy is designed as an efficient alternative. Second, to mitigate the temporal discontinuity caused by sparse keyframe sampling, we further introduce interleaved textual narratives generated from non-keyframes using off-the-shelf captioners. These narratives are inserted between keyframes based on their true temporal order, forming a coherent and compact representation. Nar-KFC thus serves as a temporal- and content-aware compression strategy that complements visual and textual modalities. Experimental results on multiple long-video benchmarks demonstrate that Nar-KFC significantly improves the performance of popular MLLMs. Code will be made publicly available.

Qiangqiang Wu, Yi Yu, Chenqi Kong et al.

With the rise of social media, vast amounts of user-uploaded videos (e.g., YouTube) are utilized as training data for Visual Object Tracking (VOT). However, the VOT community has largely overlooked video data-privacy issues, as many private videos have been collected and used for training commercial models without authorization. To alleviate these issues, this paper presents the first investigation on preventing personal video data from unauthorized exploitation by deep trackers. Existing methods for preventing unauthorized data use primarily focus on image-based tasks (e.g., image classification), directly applying them to videos reveals several limitations, including inefficiency, limited effectiveness, and poor generalizability. To address these issues, we propose a novel generative framework for generating Temporal Unlearnable Examples (TUEs), and whose efficient computation makes it scalable for usage on large-scale video datasets. The trackers trained w/ TUEs heavily rely on unlearnable noises for temporal matching, ignoring the original data structure and thus ensuring training video data-privacy. To enhance the effectiveness of TUEs, we introduce a temporal contrastive loss, which further corrupts the learning of existing trackers when using our TUEs for training. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in video data-privacy protection, with strong transferability across VOT models, datasets, and temporal matching tasks.

Hongru Chen, Jiyang Huang, Jia Wan et al.

Crowd instance segmentation is a crucial task with a wide range of applications, including surveillance and transportation. Currently, point labels are common in crowd datasets, while region labels (e.g., boxes) are rare and inaccurate. The masks obtained through segmentation help to improve the accuracy of region labels and resolve the correspondence between individual location coordinates and crowd density maps. However, directly applying currently popular large foundation models such as SAM does not yield ideal results in dense crowds. To this end, we first propose Dense Point-to-Mask Optimization (DPMO), which integrates SAM with the Nearest Neighbor Exclusive Circle (NNEC) constraint to generate dense instance segmentation from point annotations. With DPMO and manual correction, we obtain mask annotations from the existing point annotations for traditional crowd datasets. Then, to predict instance segmentation in dense crowds, we propose a Reinforced Point Selection (RPS) framework trained with Group Relative Policy Optimization (GRPO), which selects the best predicted point from a sampling of the initial point prediction. Through extensive experiments, we achieve state-of-the-art crowd instance segmentation performance on ShanghaiTech, UCF-QNRF, JHU-CROWD++, and NWPU-Crowd datasets. Furthermore, we design new loss functions supervised by masks that boost counting performance across different models, demonstrating the significant role of mask annotations in enhancing counting accuracy.

Chenyang Zhao, Jia Wan, Antoni B. Chan

Compared with the generic scenes, crowded scenes contain highly-overlapped instances, which result in: 1) more ambiguous anchors during training of object detectors, and 2) more predictions are likely to be mistakenly suppressed in post-processing during inference. To address these problems, we propose two new strategies, density-guided anchors (DGA) and density-guided NMS (DG-NMS), which uses object density maps to jointly compute optimal anchor assignments and reweighing, as well as an adaptive NMS. Concretely, based on an unbalanced optimal transport (UOT) problem, the density owned by each ground-truth object is transported to each anchor position at a minimal transport cost. And density on anchors comprises an instance-specific density distribution, from which DGA decodes the optimal anchor assignment and re-weighting strategy. Meanwhile, DG-NMS utilizes the predicted density map to adaptively adjust the NMS threshold to reduce mistaken suppressions. In the UOT, a novel overlap-aware transport cost is specifically designed for ambiguous anchors caused by overlapped neighboring objects. Extensive experiments on the challenging CrowdHuman dataset with Citypersons dataset demonstrate that our proposed density-guided detector is effective and robust to crowdedness. The code and pre-trained models will be made available later.

Yaowu Fan, Jia Wan, Tao Han et al.

Video Individual Counting (VIC) has received increasing attention for its importance in intelligent video surveillance. Existing works are limited in two aspects, i.e., dataset and method. Previous datasets are captured with fixed or rarely moving cameras with relatively sparse individuals, restricting evaluation for a highly varying view and time in crowded scenes. Existing methods rely on localization followed by association or classification, which struggle under dense and dynamic conditions due to inaccurate localization of small targets. To address these issues, we introduce the MovingDroneCrowd Dataset, featuring videos captured by fast-moving drones in crowded scenes under diverse illuminations, shooting heights and angles. We further propose a Shared Density map-guided Network (SDNet) using a Depth-wise Cross-Frame Attention (DCFA) module to directly estimate shared density maps between consecutive frames, from which the inflow and outflow density maps are derived by subtracting the shared density maps from the global density maps. The inflow density maps across frames are summed up to obtain the number of unique pedestrians in a video. Experiments on our datasets and publicly available ones show the superiority of our method over the state of the arts in highly dynamic and complex crowded scenes. Our dataset and codes have been released publicly.

Qiangqiang Wu, Antoni B. Chan

Existing deep trackers are typically trained with largescale video frames with annotated bounding boxes. However, these bounding boxes are expensive and time-consuming to annotate, in particular for large scale datasets. In this paper, we propose to learn tracking representations from single point annotations (i.e., 4.5x faster to annotate than the traditional bounding box) in a weakly supervised manner. Specifically, we propose a soft contrastive learning (SoCL) framework that incorporates target objectness prior into end-to-end contrastive learning. Our SoCL consists of adaptive positive and negative sample generation, which is memory-efficient and effective for learning tracking representations. We apply the learned representation of SoCL to visual tracking and show that our method can 1) achieve better performance than the fully supervised baseline trained with box annotations under the same annotation time cost; 2) achieve comparable performance of the fully supervised baseline by using the same number of training frames and meanwhile reducing annotation time cost by 78% and total fees by 85%; 3) be robust to annotation noise.

David Haslett, Linus Ta-Lun Huang, Leila Khalatbari et al.

As large language models increasingly mediate access to information and facilitate decision-making, they are becoming instruments in soft power competitions between global actors such as the United States and China. So far, language models seem to be aligned with the values of Western countries, but evidence for this ethical bias comes mostly from models made by American companies. The current crop of state-of-the-art models includes several made in China, so we conducted the first large-scale investigation of how models made in China and the USA align with people from China and the USA. We elicited responses to the Moral Foundations Questionnaire 2.0 and the World Values Survey from ten Chinese models and ten American models, and we compared their responses to responses from thousands of Chinese and American people. We found that all models respond to both surveys more like American people than like Chinese people. This skew toward American values is only slightly mitigated when prompting the models in Chinese or imposing a Chinese persona on the models. These findings have important implications for a near future in which large language models generate much of the content people consume and shape normative influence in geopolitics.

Qi Zhang, Bin Li, Antoni B. Chan et al.

Multi-view crowd counting and localization fuse the input multi-views for estimating the crowd number or locations on the ground. Existing methods mainly focus on accurately predicting on the crowd shown in the input views, which neglects the problem of choosing the `best' camera views to perceive all crowds well in the scene. Besides, existing view selection methods require massive labeled views and images, and lack the ability for cross-scene settings, reducing their application scenarios. Thus, in this paper, we study the view selection issue for better scene-level multi-view crowd counting and localization results with cross-scene ability and limited label demand, instead of input-view-level results. We first propose an independent view selection method (IVS) that considers view and scene geometries in the view selection strategy and conducts the view selection, labeling, and downstream tasks independently. Based on IVS, we also put forward an active view selection method (AVS) that jointly optimizes the view selection, labeling, and downstream tasks. In AVS, we actively select the labeled views and consider both the view/scene geometries and the predictions of the downstream task models in the view selection process. Experiments on multi-view counting and localization tasks demonstrate the cross-scene and the limited label demand advantages of the proposed active view selection method (AVS), outperforming existing methods and with wider application scenarios.

Xianrui Li, Yufei Cui, Jun Li et al.

Advances in medical imaging and deep learning have propelled progress in whole slide image (WSI) analysis, with multiple instance learning (MIL) showing promise for efficient and accurate diagnostics. However, conventional MIL models often lack adaptability to evolving datasets, as they rely on static training that cannot incorporate new information without extensive retraining. Applying continual learning (CL) to MIL models is a possible solution, but often sees limited improvements. In this paper, we analyze CL in the context of attention MIL models and find that the model forgetting is mainly concentrated in the attention layers of the MIL model. Using the results of this analysis we propose two components for improving CL on MIL: Attention Knowledge Distillation (AKD) and the Pseudo-Bag Memory Pool (PMP). AKD mitigates catastrophic forgetting by focusing on retaining attention layer knowledge between learning sessions, while PMP reduces the memory footprint by selectively storing only the most informative patches, or ``pseudo-bags'' from WSIs. Experimental evaluations demonstrate that our method significantly improves both accuracy and memory efficiency on diverse WSI datasets, outperforming current state-of-the-art CL methods. This work provides a foundation for CL in large-scale, weakly annotated clinical datasets, paving the way for more adaptable and resilient diagnostic models.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Recent advances in image captioning have focused on enhancing accuracy by substantially increasing the dataset and model size. While conventional captioning models exhibit high performance on established metrics such as BLEU, CIDEr, and SPICE, the capability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employed contrastive learning or re-weighted the ground-truth captions. However, these approaches often overlook the relationships among objects in a similar image group (e.g., items or properties within the same album or fine-grained events). In this paper, we introduce a novel approach to enhance the distinctiveness of image captions, namely Group-based Differential Distinctive Captioning Method, which visually compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we introduce a Group-based Differential Memory Attention (GDMA) module, designed to identify and emphasize object features in an image that are uniquely distinguishable within its image group, i.e., those exhibiting low similarity with objects in other images. This mechanism ensures that such unique object features are prioritized during caption generation for the image, thereby enhancing the distinctiveness of the resulting captions. To further refine this process, we select distinctive words from the ground-truth captions to guide both the language decoder and the GDMA module. Additionally, we propose a new evaluation metric, the Distinctive Word Rate (DisWordRate), to quantitatively assess caption distinctiveness. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves state-of-the-art performance on distinctiveness while not excessively sacrificing accuracy...

Runling Long, Yunlong Wang, Jia Wan et al.

Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectiveness is limited. This is mainly because most existing crowd counting datasets on which the methods are trained are based on passive cameras, restricting their ability to fully sense the environment. Recently, embodied navigation methods have shown significant potential in precise object detection in interactive scenes. These methods incorporate active camera settings, holding promise in addressing the fundamental issues in crowd counting. However, most existing methods are designed for indoor navigation, showing unknown performance in analyzing complex object distribution in large scale scenes, such as crowds. Besides, most existing embodied navigation datasets are indoor scenes with limited scale and object quantity, preventing them from being introduced into dense crowd analysis. Based on this, a novel task, Embodied Crowd Counting (ECC), is proposed. We first build up an interactive simulator, Embodied Crowd Counting Dataset (ECCD), which enables large scale scenes and large object quantity. A prior probability distribution that approximates realistic crowd distribution is introduced to generate crowds. Then, a zero-shot navigation method (ZECC) is proposed. This method contains a MLLM driven coarse-to-fine navigation mechanism, enabling active Z-axis exploration, and a normal-line-based crowd distribution analysis method for fine counting. Experimental results against baselines show that the proposed method achieves the best trade-off between counting accuracy and navigation cost.

Ying Xiong, Linjing Liu, Yufei Cui et al.

Gene expression profiling provides profound insights into molecular mechanisms, but its time-consuming and costly nature often presents significant challenges. In contrast, whole-slide hematoxylin and eosin (H&E) stained histological images are readily accessible and allow for detailed examinations of tissue structure and composition at the microscopic level. Recent advancements have utilized these histological images to predict spatially resolved gene expression profiles. However, state-of-the-art works treat gene expression prediction as a multi-output regression problem, where each gene is learned independently with its own weights, failing to capture the shared dependencies and co-expression patterns between genes. Besides, existing works can only predict gene expression values for genes seen during training, limiting their ability to generalize to new, unseen genes. To address the above limitations, this paper presents GeneQuery, which aims to solve this gene expression prediction task in a question-answering (QA) manner for better generality and flexibility. Specifically, GeneQuery takes gene-related texts as queries and whole-slide images as contexts and then predicts the queried gene expression values. With such a transformation, GeneQuery can implicitly estimate the gene distribution by introducing the gene random variable. Besides, the proposed GeneQuery consists of two architecture implementations, i.e., spot-aware GeneQuery for capturing patterns between images and gene-aware GeneQuery for capturing patterns between genes. Comprehensive experiments on spatial transcriptomics datasets show that the proposed GeneQuery outperforms existing state-of-the-art methods on known and unseen genes. More results also demonstrate that GeneQuery can potentially analyze the tissue structure.

Guoyang Liu, Jindi Zhang, Antoni B. Chan et al.

We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness. We first developed new gradient-based XAI methods for object detection models to generate object-specific explanations by extending the current methods for image classification models. Interestingly, while these gradient-based methods worked well for explaining image classification models, when being used for explaining object detection models, the resulting saliency maps generally had lower faithfulness than human attention maps when performing the same task. We then developed Human Attention-Guided XAI (HAG-XAI) to learn from human attention how to best combine explanatory information from the models to enhance explanation plausibility by using trainable activation functions and smoothing kernels to maximize XAI saliency map's similarity to human attention maps. While for image classification models, HAG-XAI enhanced explanation plausibility at the expense of faithfulness, for object detection models it enhanced plausibility and faithfulness simultaneously and outperformed existing methods. The learned functions were model-specific, well generalizable to other databases.

Zhirui Dai, Yuepeng Jiang, Yi Li et al.

Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub.

Jiuniu Wang, Wenjia Xu, Qingzhong Wang et al.

Describing images using natural language is widely known as image captioning, which has made consistent progress due to the development of computer vision and natural language generation techniques. Though conventional captioning models achieve high accuracy based on popular metrics, i.e., BLEU, CIDEr, and SPICE, the ability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employ contrastive learning or re-weighted the ground-truth captions, which focuses on one single input image. However, the relationships between objects in a similar image group (e.g., items or properties within the same album or fine-grained events) are neglected. In this paper, we improve the distinctiveness of image captions using a Group-based Distinctive Captioning Model (GdisCap), which compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i.e., with low similarity to objects in other images). These unique object features are highlighted when generating captions, resulting in more distinctive captions. Furthermore, the distinctive words in the ground-truth captions are selected to supervise the language decoder and GMA. Finally, we propose a new evaluation metric, distinctive word rate (DisWordRate) to measure the distinctiveness of captions. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves the state-of-the-art performance on both accuracy and distinctiveness. Results of a user study agree with the quantitative evaluation and demonstrate the rationality of the new metric DisWordRate.

Xueying Zhan, Qing Li, Antoni B. Chan

Active learning aims to achieve greater accuracy with less training data by selecting the most useful data samples from which it learns. Single-criterion based methods (i.e., informativeness and representativeness based methods) are simple and efficient; however, they lack adaptability to different real-world scenarios. In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i.e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types. We consider the selection process as a Determinantal Point Process, which good balance among these criteria. We refine the query selection strategy by both selecting the hardest unlabeled data sample and biasing towards the classifiers that are more suitable for the current data distribution. In addition, we also consider the dependencies and relationships between these data points in data selection by means of centroidbased clustering approaches. Through evaluations on synthetic and real-world datasets, we show that our method performs significantly better and is more stable than other multiple-criteria based AL algorithms.

Ziquan Liu, Yufei Cui, Jia Wan et al.

Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are invariant to weight rescaling due to the normalization. In this paper, we demonstrate that the practical usage of weight decay still has some unsolved problems in spite of existing theoretical work on explaining the effect of weight decay in BN-DNNs. On the one hand, when the non-adaptive learning rate e.g. SGD with momentum is used, the effective learning rate continues to increase even after the initial training stage, which leads to an overfitting effect in many neural architectures. On the other hand, in both SGDM and adaptive learning rate optimizers e.g. Adam, the effect of weight decay on generalization is quite sensitive to the hyperparameter. Thus, finding an optimal weight decay parameter requires extensive parameter searching. To address those weaknesses, we propose to regularize the weight norm using a simple yet effective weight rescaling (WRS) scheme as an alternative to weight decay. WRS controls the weight norm by explicitly rescaling it to the unit norm, which prevents a large increase to the gradient but also ensures a sufficiently large effective learning rate to improve generalization. On a variety of computer vision applications including image classification, object detection, semantic segmentation and crowd counting, we show the effectiveness and robustness of WRS compared with weight decay, implicit weight rescaling (weight standardization) and gradient projection (AdamP).

Yufei Cui, Yu Mao, Ziquan Liu et al.

Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for: I. Constructing nested nets: the nested nets are neural networks whose architectures can be adjusted instantly during testing time, e.g., based on computational constraints. The nested dropout implicitly ranks the network parameters, generating a set of sub-networks such that any smaller sub-network forms the basis of a larger one. II. Learning ordered representation: the nested dropout applied to the latent representation of a generative model (e.g., auto-encoder) ranks the features, enforcing explicit order of the dense representation over dimensions. However, the dropout rate is fixed as a hyper-parameter during the whole training process. For nested nets, when network parameters are removed, the performance decays in a human-specified trajectory rather than in a trajectory learned from data. For generative models, the importance of features is specified as a constant vector, restraining the flexibility of representation learning. To address the problem, we focus on the probabilistic counterpart of the nested dropout. We propose a variational nested dropout (VND) operation that draws samples of multi-dimensional ordered masks at a low cost, providing useful gradients to the parameters of nested dropout. Based on this approach, we design a Bayesian nested neural network that learns the order knowledge of the parameter distributions. We further exploit the VND under different generative models for learning ordered latent distributions. In experiments, we show that the proposed approach outperforms the nested network in terms of accuracy, calibration, and out-of-domain detection in classification tasks. It also outperforms the related generative models on data generation tasks.

Qi Zhang, Antoni B. Chan

Crowd counting in single-view images has achieved outstanding performance on existing counting datasets. However, single-view counting is not applicable to large and wide scenes (e.g., public parks, long subway platforms, or event spaces) because a single camera cannot capture the whole scene in adequate detail for counting, e.g., when the scene is too large to fit into the field-of-view of the camera, too long so that the resolution is too low on faraway crowds, or when there are too many large objects that occlude large portions of the crowd. Therefore, to solve the wide-area counting task requires multiple cameras with overlapping fields-of-view. In this paper, we propose a deep neural network framework for multi-view crowd counting, which fuses information from multiple camera views to predict a scene-level density map on the ground-plane of the 3D world. We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales. A rotation selection module further ensures consistent rotation alignment of the features. We test our 3 fusion models on 3 multi-view counting datasets, PETS2009, DukeMTMC, and a newly collected multi-view counting dataset containing a crowded street intersection. Our methods achieve state-of-the-art results compared to other multi-view counting baselines.

Ziquan Liu, Yufei Cui, Antoni B. Chan

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is ineffective at penalizing the intrinsic norms of weights for networks with positively homogeneous activation functions, such as linear, ReLU and max-pooling functions. As a result of homogeneity, functions specified by the networks are invariant to the shifting of weight scales between layers. The ineffective regularizers are sensitive to such shifting and thus poorly regularize the model capacity, leading to overfitting. To address this shortcoming, we propose an improved regularizer that is invariant to weight scale shifting and thus effectively constrains the intrinsic norm of a neural network. The derived regularizer is an upper bound for the input gradient of the network so minimizing the improved regularizer also benefits the adversarial robustness. Residual connections are also considered and we show that our regularizer also forms an upper bound to input gradients of such a residual network. We demonstrate the efficacy of our proposed regularizer on various datasets and neural network architectures at improving generalization and adversarial robustness.

Weihong Ren, Xinchao Wang, Jiandong Tian et al.

State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to obtain accurate detections due to heavy occlusions and high crowd density. In this paper, we propose a new MOT paradigm, tracking-by-counting, tailored for crowded scenes. Using crowd density maps, we jointly model detection, counting, and tracking of multiple targets as a network flow program, which simultaneously finds the global optimal detections and trajectories of multiple targets over the whole video. This is in contrast to prior MOT methods that either ignore the crowd density and thus are prone to errors in crowded scenes, or rely on a suboptimal two-step process using heuristic density-aware point-tracks for matching targets.Our approach yields promising results on public benchmarks of various domains including people tracking, cell tracking, and fish tracking.