Bing Li

Haozhe Liu, Bing Li, Haoqian Wu et al. · tencent-ai

Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs. Different from existing methods, we propose to generalize the discriminator as feature embedding and maximize the entropy of distributions in the embedding space learned by the discriminator. Specifically, two regularization terms, i.e., Deep Local Linear Embedding (DLLE) and Deep Isometric feature Mapping (DIsoMap), are designed to encourage the discriminator to learn the structural information embedded in the data, such that the embedding space learned by the discriminator can be well-formed. Based on the well-learned embedding space supported by the discriminator, a non-parametric entropy estimator is designed to efficiently maximize the entropy of embedding vectors, playing as an approximation of maximizing the entropy of the generated distribution. By improving the discriminator and maximizing the distance of the most similar samples in the embedding space, our pipeline effectively reduces the mode collapse without sacrificing the quality of generated samples. Extensive experimental results show the effectiveness of our method, which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs. 12.43 in FID) and surpasses the recent state-of-the-art energy-based model on the ANIME-FACE dataset (2.80 vs. 2.26 in Inception score). The code is available at https://github.com/HaozheLiu-ST/MEE

Haozhe Liu, Wentian Zhang, Jinheng Xie et al. · tencent-ai

Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which is unseen and Out-Of-the-Distribution (OOD). To address this issue, we propose a novel "Decoupled-Mixup" method to train CNN models for OOD visual recognition. Different from previous work combining pairs of images homogeneously, our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions of image pairs to train CNN models. Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair. To further improve the generalization ability of trained models, we propose to disentangle discriminative and noise-prone regions in frequency-based and context-based fashions. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts, where our method achieves 85.76\% top-1 accuracy in Track-1 and 79.92\% in Track-2 in the NICO Challenge. The source code is available at https://github.com/HaozheLiu-ST/NICOChallenge-OOD-Classification.

Li Yang, Yan Xu, Chunfeng Yuan et al.

Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They base the visual grounding on the features from pre-generated proposals or anchors, and fuse these features with the text embeddings to locate the target mentioned by the text. However, modeling the visual features from these predefined locations may fail to fully exploit the visual context and attribute information in the text query, which limits their performance. In this paper, we propose a transformer-based framework for accurate visual grounding by establishing text-conditioned discriminative features and performing multi-stage cross-modal reasoning. Specifically, we develop a visual-linguistic verification module to focus the visual features on regions relevant to the textual descriptions while suppressing the unrelated areas. A language-guided feature encoder is also devised to aggregate the visual contexts of the target object to improve the object's distinctiveness. To retrieve the target from the encoded visual features, we further propose a multi-stage cross-modal decoder to iteratively speculate on the correlations between the image and text for accurate target localization. Extensive experiments on five widely used datasets validate the efficacy of our proposed components and demonstrate state-of-the-art performance. Our code is public at https://github.com/yangli18/VLTVG.

Jingcun Wang, Bing Li, Grace Li Zhang

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained platforms, e.g., edge devices. To address this challenge, in this paper, we propose a class-based early-exit for dynamic inference. Instead of pushing DNNs to make a dynamic decision at intermediate layers, we take advantage of the learned features in these layers to exclude as many irrelevant classes as possible, so that later layers only have to determine the target class among the remaining classes. When only one class remains at a layer, this class is the corresponding classification result. Experimental results demonstrate the computational cost of DNNs in inference can be reduced significantly with the proposed early-exit technique. The codes can be found at https://github.com/HWAI-TUDa/EarlyClassExclusion.

Yutong Kou, Jin Gao, Bing Li et al.

Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size. To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa. This enables us to solve the dilemma of attending to a larger visual field while retaining more raw information for the target despite a smaller input size. Our formulation for the non-uniform resizing can be efficiently solved through quadratic programming (QP) and naturally integrated into most of the crop-based local trackers. Comprehensive experiments on five challenging datasets based on two kinds of transformer trackers, \ie, OSTrack and TransT, demonstrate consistent improvements over them. In particular, applying our method to the speed-oriented version of OSTrack even outperforms its performance-oriented counterpart by 0.6% AUC on TNL2K, while running 50% faster and saving over 55% MACs. Codes and models are available at https://github.com/Kou-99/ZoomTrack.

Tongkun Liu, Bing Li, Zhuo Zhao et al.

Reconstruction-based methods are widely explored in industrial visual anomaly detection. Such methods commonly require the model to well reconstruct the normal patterns but fail in the anomalies, and thus the anomalies can be detected by evaluating the reconstruction errors. However, in practice, it's usually difficult to control the generalization boundary of the model. The model with an overly strong generalization capability can even well reconstruct the abnormal regions, making them less distinguishable, while the model with a poor generalization capability can not reconstruct those changeable high-frequency components in the normal regions, which ultimately leads to false positives. To tackle the above issue, we propose a new reconstruction network where we reconstruct the original RGB image from its gray value edges (EdgRec). Specifically, this is achieved by an UNet-type denoising autoencoder with skip connections. The input edge and skip connections can well preserve the high-frequency information in the original image. Meanwhile, the proposed restoration task can force the network to memorize the normal low-frequency and color information. Besides, the denoising design can prevent the model from directly copying the original high-frequent components. To evaluate the anomalies, we further propose a new interpretable hand-crafted evaluation function that considers both the color and gradient differences. Our method achieves competitive results on the challenging benchmark MVTec AD (97.8\% for detection and 97.7\% for localization, AUROC). In addition, we conduct experiments on the MVTec 3D-AD dataset and show convincing results using RGB images only. Our code will be available at https://github.com/liutongkun/EdgRec.

Yufan Liu, Jiajiong Cao, Bing Li et al.

Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill complementary knowledge from Transformer to convolutional neural network (CNN). However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN. They may not be suitable when applying to cross-architecture scenarios, such as from Transformer to CNN. To deal with this problem, a novel cross-architecture knowledge distillation method is proposed. Specifically, instead of directly mimicking output/intermediate features of the teacher, partially cross attention projector and group-wise linear projector are introduced to align the student features with the teacher's in two projected feature spaces. And a multi-view robust training scheme is further presented to improve the robustness and stability of the framework. Extensive experiments show that the proposed method outperforms 14 state-of-the-arts on both small-scale and large-scale datasets.

Shaokui Wei, Jiayin Liu, Bing Li et al.

We study the fair regression problem under the notion of Mean Parity (MP) fairness, which requires the conditional mean of the learned function output to be constant with respect to the sensitive attributes. We address this problem by leveraging reproducing kernel Hilbert space (RKHS) to construct the functional space whose members are guaranteed to satisfy the fairness constraints. The proposed functional space suggests a closed-form solution for the fair regression problem that is naturally compatible with multiple sensitive attributes. Furthermore, by formulating the fairness-accuracy tradeoff as a relaxed fair regression problem, we derive a corresponding regression function that can be implemented efficiently and provides interpretable tradeoffs. More importantly, under some mild assumptions, the proposed method can be applied to regression problems with a covariance-based notion of fairness. Experimental results on benchmark datasets show the proposed methods achieve competitive and even superior performance compared with several state-of-the-art methods.

Linkun Fan, Fazhi He, Qing Guo et al.

For saving cost, many deep neural networks (DNNs) are trained on third-party datasets downloaded from internet, which enables attacker to implant backdoor into DNNs. In 2D domain, inherent structures of different image formats are similar. Hence, backdoor attack designed for one image format will suite for others. However, when it comes to 3D world, there is a huge disparity among different 3D data structures. As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene. Therefore, this paper designs a uniform backdoor pattern: NRBdoor (Noisy Rotation Backdoor) which is able to adapt for heterogeneous 3D data structures. Specifically, we start from the unit rotation and then search for the optimal pattern by noise generation and selection process. The proposed NRBdoor is natural and imperceptible, since rotation is a common operation which usually contains noise due to both the miss match between a pair of points and the sensor calibration error for real-world 3D scene. Extensive experiments on 3D mesh and point cloud show that the proposed NRBdoor achieves state-of-the-art performance, with negligible shape variation.

Shaoru Wang, Jin Gao, Bing Li et al.

Deep learning methods require massive of annotated data for optimizing parameters. For example, datasets attached with accurate bounding box annotations are essential for modern object detection tasks. However, labeling with such pixel-wise accuracy is laborious and time-consuming, and elaborate labeling procedures are indispensable for reducing man-made noise, involving annotation review and acceptance testing. In this paper, we focus on the impact of noisy location annotations on the performance of object detection approaches and aim to, on the user side, reduce the adverse effect of the noise. First, noticeable performance degradation is experimentally observed for both one-stage and two-stage detectors when noise is introduced to the bounding box annotations. For instance, our synthesized noise results in performance decrease from 38.9% AP to 33.6% AP for FCOS detector on COCO test split, and 37.8%AP to 33.7%AP for Faster R-CNN. Second, a self-correction technique based on a Bayesian filter for prediction ensemble is proposed to better exploit the noisy location annotations following a Teacher-Student learning paradigm. Experiments for both synthesized and real-world scenarios consistently demonstrate the effectiveness of our approach, e.g., our method increases the degraded performance of the FCOS detector from 33.6% AP to 35.6% AP on COCO.

Bing Li, Jiaxin Chen, Dongming Zhang et al.

Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion vectors and residuals). However, this task severely suffers from the coarse and noisy dynamics and the insufficient fusion of the heterogeneous RGB and motion modalities. To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net). It follows the two-stream architecture, i.e. one for the RGB modality and the other for the motion modality. Particularly, the motion stream employs a multi-scale block embedded with a denoising module to enhance representation learning. The interaction between the two streams is then strengthened by introducing the Selective Motion Complement (SMC) and Cross-Modality Augment (CMA) modules, where SMC complements the RGB modality with spatio-temporally attentive local motion features and CMA further combines the two modalities with selective feature augmentation. Extensive experiments on the UCF-101, HMDB-51 and Kinetics-400 benchmarks demonstrate the effectiveness and efficiency of MEACI-Net.

Wenhao Sun, Grace Li Zhang, Huaxi Gu et al.

In deep neural networks (DNNs), there are a huge number of weights and multiply-and-accumulate (MAC) operations. Accordingly, it is challenging to apply DNNs on resource-constrained platforms, e.g., mobile phones. Quantization is a method to reduce the size and the computational complexity of DNNs. Existing quantization methods either require hardware overhead to achieve a non-uniform quantization or focus on model-wise and layer-wise uniform quantization, which are not as fine-grained as filter-wise quantization. In this paper, we propose a class-based quantization method to determine the minimum number of quantization bits for each filter or neuron in DNNs individually. In the proposed method, the importance score of each filter or neuron with respect to the number of classes in the dataset is first evaluated. The larger the score is, the more important the filter or neuron is and thus the larger the number of quantization bits should be. Afterwards, a search algorithm is adopted to exploit the different importance of filters and neurons to determine the number of quantization bits of each filter or neuron. Experimental results demonstrate that the proposed method can maintain the inference accuracy with low bit-width quantization. Given the same number of quantization bits, the proposed method can also achieve a better inference accuracy than the existing methods.

Zongyang Ma, Ziqi Zhang, Yuxin Chen et al.

Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.

Wenhao Sun, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have successfully been applied in many fields in the past decades. However, the increasing number of multiply-and-accumulate (MAC) operations in DNNs prevents their application in resource-constrained and resource-varying platforms, e.g., mobile phones and autonomous vehicles. In such platforms, neural networks need to provide acceptable results quickly and the accuracy of the results should be able to be enhanced dynamically according to the computational resources available in the computing system. To address these challenges, we propose a design framework called SteppingNet. SteppingNet constructs a series of subnets whose accuracy is incrementally enhanced as more MAC operations become available. Therefore, this design allows a trade-off between accuracy and latency. In addition, the larger subnets in SteppingNet are built upon smaller subnets, so that the results of the latter can directly be reused in the former without recomputation. This property allows SteppingNet to decide on-the-fly whether to enhance the inference accuracy by executing further MAC operations. Experimental results demonstrate that SteppingNet provides an effective incremental accuracy improvement and its inference accuracy consistently outperforms the state-of-the-art work under the same limit of computational resources.

Yifan Lu, Ziqi Zhang, Yuxin Chen et al.

The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of PIC 4th Challenge.

Chuangtao Chen, Grace Li Zhang, Xunzhao Yin et al.

Deep neural networks (DNNs) have been widely deployed across diverse domains such as computer vision and natural language processing. However, the impressive accomplishments of DNNs have been realized alongside extensive computational demands, thereby impeding their applicability on resource-constrained devices. To address this challenge, many researchers have been focusing on basic neuron structures, the fundamental building blocks of neural networks, to alleviate the computational and storage cost. In this work, an efficient quadratic neuron architecture distinguished by its enhanced utilization of second-order computational information is introduced. By virtue of their better expressivity, DNNs employing the proposed quadratic neurons can attain similar accuracy with fewer neurons and computational cost. Experimental results have demonstrated that the proposed quadratic neuron structure exhibits superior computational and storage efficiency across various tasks when compared with both linear and non-linear neurons in prior work.

Cheng Feng, Congxuan Zhang, Zhen Chen et al.

Depth sensing is of paramount importance for unmanned aerial and autonomous vehicles. Nonetheless, contemporary monocular depth estimation methods employing complex deep neural networks within Convolutional Neural Networks are inadequately expedient for real-time inference on embedded platforms. This paper endeavors to surmount this challenge by proposing two efficient and lightweight architectures, RT-MonoDepth and RT-MonoDepth-S, thereby mitigating computational complexity and latency. Our methodologies not only attain accuracy comparable to prior depth estimation methods but also yield faster inference speeds. Specifically, RT-MonoDepth and RT-MonoDepth-S achieve frame rates of 18.4&30.5 FPS on NVIDIA Jetson Nano and 253.0&364.1 FPS on Jetson AGX Orin, utilizing a single RGB image of resolution 640x192. The experimental results underscore the superior accuracy and faster inference speed of our methods in comparison to existing fast monocular depth estimation methodologies on the KITTI dataset.

Zewen Chen, Juan Wang, Wen Wang et al.

Existing Image Quality Assessment (IQA) methods achieve remarkable success in analyzing quality for overall image, but few works explore quality analysis for Regions of Interest (ROIs). The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality. This paper proposes a novel network, SEAGULL, which can SEe and Assess ROIs quality with GUidance from a Large vision-Language model. SEAGULL incorporates a vision-language model (VLM), masks generated by Segment Anything Model (SAM) to specify ROIs, and a meticulously designed Mask-based Feature Extractor (MFE) to extract global and local tokens for specified ROIs, enabling accurate fine-grained IQA for ROIs. Moreover, this paper constructs two ROI-based IQA datasets, SEAGULL-100w and SEAGULL-3k, for training and evaluating ROI-based IQA. SEAGULL-100w comprises about 100w synthetic distortion images with 33 million ROIs for pre-training to improve the model's ability of regional quality perception, and SEAGULL-3k contains about 3k authentic distortion ROIs to enhance the model's ability to perceive real world distortions. After pre-training on SEAGULL-100w and fine-tuning on SEAGULL-3k, SEAGULL shows remarkable performance on fine-grained ROI quality assessment. Code and datasets are publicly available at the https://github.com/chencn2020/Seagull.

Manyi Li, Renshuai Tao, Yufan Liu et al.

With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.

Zhimin Chen, Longlong Jing, Yingwei Li et al.

Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models. Specifically, our method employs semantic masks from foundation models to guide the masking and reconstruction process for the masked autoencoder, enabling more focused attention on foreground representations. Moreover, we bridge the 3D-text gap at the scene level using image captioning foundation models, thereby facilitating scene-level knowledge distillation. We further extend this bridging effort by introducing an innovative object-level knowledge distillation method that harnesses highly accurate object-level masks and semantic text data from foundation models. Our methodology significantly surpasses the performance of existing state-of-the-art methods in 3D object detection and semantic segmentation tasks. For instance, on the ScanNet dataset, Bridge3D improves the baseline by a notable margin of 6.3%. Code will be available at: https://github.com/Zhimin-C/Bridge3D

Tongkun Liu, Bing Li, Xiao Du et al.

Industrial visual inspection aims at detecting surface defects in products during the manufacturing process. Although existing anomaly detection models have shown great performance on many public benchmarks, their limited adjustability and ability to detect logical anomalies hinder their broader use in real-world settings. To this end, in this paper, we propose a novel component-aware anomaly detection framework (ComAD) which can simultaneously achieve adjustable and logical anomaly detection for industrial scenarios. Specifically, we propose to segment images into multiple components based on a lightweight and nearly training-free unsupervised semantic segmentation model. Then, we design an interpretable logical anomaly detection model through modeling the metrological features of each component and their relationships. Despite its simplicity, our framework achieves state-of-the-art performance on image-level logical anomaly detection. Meanwhile, segmenting a product image into multiple components provides a novel perspective for industrial visual inspection, demonstrating great potential in model customization, noise resistance, and anomaly classification. The code will be available at https://github.com/liutongkun/ComAD.

Linhan Zhang, Qian Chen, Wen Wang et al.

Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art (SOTA) methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document. We further develop a KPE-oriented BERT (KPEBERT) model by proposing a novel self-supervised contrastive learning method, which is more compatible to MDERank than vanilla BERT. Comprehensive evaluations on six KPE benchmarks demonstrate that the proposed MDERank outperforms state-of-the-art unsupervised KPE approach by average 1.80 $F1@15$ improvement. MDERank further benefits from KPEBERT and overall achieves average 3.53 $F1@15$ improvement over the SOTA SIFRank. Our code is available at \url{https://github.com/LinhanZ/mderank}.

Zhipeng Zhang, Yihao Liu, Xiao Wang et al.

Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants. Besides the remarkable success, it is important to note that the heuristic matching network design relies heavily on expert experience. Moreover, we experimentally find that one sole matching operator is difficult to guarantee stable tracking in all challenging environments. Thus, in this work, we introduce six novel matching operators from the perspective of feature fusion instead of explicit similarity learning, namely Concatenation, Pointwise-Addition, Pairwise-Relation, FiLM, Simple-Transformer and Transductive-Guidance, to explore more feasibility on matching operator selection. The analyses reveal these operators' selective adaptability on different environment degradation types, which inspires us to combine them to explore complementary features. To this end, we propose binary channel manipulation (BCM) to search for the optimal combination of these operators. BCM determines to retrain or discard one operator by learning its contribution to other tracking steps. By inserting the learned matching networks to a strong baseline tracker Ocean, our model achieves favorable gains by $67.2 \rightarrow 71.4$, $52.6 \rightarrow 58.3$, $70.3 \rightarrow 76.0$ success on OTB100, LaSOT, and TrackingNet, respectively. Notably, Our tracker, dubbed AutoMatch, uses less than half of training data/time than the baseline tracker, and runs at 50 FPS using PyTorch. Code and model will be released at https://github.com/JudasDie/SOTS.

Li Yang, Yan Xu, Shaoru Wang et al.

Recent one-stage object detectors follow a per-pixel prediction approach that predicts both the object category scores and boundary positions from every single grid location. However, the most suitable positions for inferring different targets, i.e., the object category and boundaries, are generally different. Predicting all these targets from the same grid location thus may lead to sub-optimal results. In this paper, we analyze the suitable inference positions for object category and boundaries, and propose a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm. Our PDNet with the prediction decoupling mechanism encodes different targets separately in different locations. A learnable prediction collection module is devised with two sets of dynamic points, i.e., dynamic boundary points and semantic points, to collect and aggregate the predictions from the favorable regions for localization and classification. We adopt a two-step strategy to learn these dynamic point positions, where the prior positions are estimated for different targets first, and the network further predicts residual offsets to the positions with better perceptions of the object properties. Extensive experiments on the MS COCO benchmark demonstrate the effectiveness and efficiency of our method. With a single ResNeXt-64x4d-101-DCN as the backbone, our detector achieves 50.1 AP with single-scale testing, which outperforms the state-of-the-art methods by an appreciable margin under the same experimental settings.Moreover, our detector is highly efficient as a one-stage framework. Our code is public at https://github.com/yangli18/PDNet.

Chao Liang, Zhipeng Zhang, Xue Zhou et al.

Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destroy task-dependent representations learning. To tackle this problem, we propose a novel reciprocal network (REN) with a self-relation and cross-relation design so that to impel each branch to better learn task-dependent representations. The proposed model aims to alleviate the deleterious tasks competition, meanwhile improve the cooperation between detection and ReID. Furthermore, we introduce a scale-aware attention network (SAAN) that prevents semantic level misalignment to improve the association capability of ID embeddings. By integrating the two delicately designed networks into a one-shot online MOT system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The complete code has been released at https://github.com/JudasDie/SOTS.

Zhipeng Zhang, Houwen Peng, Jianlong Fu et al.

Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., $IoU \geq0.6$). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at https://github.com/researchmm/TracKit.

Zhongjian Hu, Peng Yang, Bing Li et al.

Recently, Large Language Models (LLMs) have been used for knowledge-based Visual Question Answering (VQA). Despite the encouraging results of previous studies, prior methods prompt LLMs to predict answers directly, neglecting intermediate thought processes. We argue that prior methods do not sufficiently activate the capacities of LLMs. We propose a framework called PLRH that Prompts LLMs with Rationale Heuristics for knowledge-based VQA. The PLRH prompts LLMs with Chain of Thought (CoT) to generate rationale heuristics, i.e., intermediate thought processes, and then leverages the rationale heuristics to inspire LLMs to predict answers. Experiments show that our approach outperforms the existing baselines by more than 2.2 and 2.1 on OK-VQA and A-OKVQA, respectively.

Mingyang Chen, Bo Huang, Junda Lu et al.

Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this paper, we approach the dataset distillation problem from a novel perspective: we regard minimizing the prediction discrepancy on the real data distribution between models, which are respectively trained on the large original dataset and on the small distilled dataset, as a conduit for condensing information from the raw data into the distilled version. An adversarial framework is proposed to solve the problem efficiently. In contrast to existing distillation methods involving nested optimization or long-range gradient unrolling, our approach hinges on single-level optimization. This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6.5GB of GPU memory. Under the optimal tradeoff strategy, it requires only 2.5$\times$ less memory and 5$\times$ less runtime compared to the state-of-the-art. Empirically, our method can produce synthetic datasets just 10% the size of the original, yet achieve, on average, 94% of the test accuracy of models trained on the full original datasets including ImageNet-1K, significantly surpassing state-of-the-art. Additionally, extensive tests reveal that our distilled datasets excel in cross-architecture generalization capabilities.

Yifan Lu, Ziqi Zhang, Chunfeng Yuan et al.

Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergistic tasks, i.e., caption generation and an auxiliary task of concept combination prediction providing extra semantic supervision. Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction. Furthermore, we apply a diversity regularization term on concepts to encourage the model to generate semantically diverse captions with various concept combinations. These two tasks share multiple semantics-specific encodings as input, which are obtained by iterative interaction between visual features and conceptual queries. The correspondence between the generated captions and specific concept combinations further guarantees the interpretability of our model. Extensive experiments on benchmark datasets show that the proposed SCG-SP achieves state-of-the-art (SOTA) performance under both relevance and diversity metrics.

Zhongjian Hu, Peng Yang, Bing Li et al.

Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA). However existing methods still have challenges: the inability to use external tools autonomously, and the inability to work in teams. Humans tend to know whether they need to use external tools when they encounter a new question, e.g., they tend to be able to give a direct answer to a familiar question, whereas they tend to use tools such as search engines when they encounter an unfamiliar question. In addition, humans also tend to collaborate and discuss with others to get better answers. Inspired by this, we propose the multi-agent voting framework. We design three LLM-based agents that simulate different levels of staff in a team, and assign the available tools according to the levels. Each agent provides the corresponding answer, and finally all the answers provided by the agents are voted to get the final answer. Experiments on OK-VQA and A-OKVQA show that our approach outperforms other baselines by 2.2 and 1.0, respectively.

Bing Li, Wuqi Wang, Yanan Zhang et al.

LiDAR-based 3D object detectors are fundamental to autonomous driving, where failing to detect objects poses severe safety risks. Developing effective 3D adversarial attacks is essential for thoroughly testing these detection systems and exposing their vulnerabilities before real-world deployment. However, existing adversarial attacks that add optimized perturbations to 3D points have two critical limitations: they rarely cause complete object disappearance and prove difficult to implement in physical environments. We introduce the text-to-3D adversarial generation method, a novel approach enabling physically realizable attacks that can generate 3D models of objects truly invisible to LiDAR detectors and be easily realized in the real world. Specifically, we present the first empirical study that systematically investigates the factors influencing detection vulnerability by manipulating the topology, connectivity, and intensity of individual pedestrian 3D models and combining pedestrians with multiple objects within the CARLA simulation environment. Building on the insights, we propose the physically-informed text-to-3D adversarial generation (Phy3DAdvGen) that systematically optimizes text prompts by iteratively refining verbs, objects, and poses to produce LiDAR-invisible pedestrians. To ensure physical realizability, we construct a comprehensive object pool containing 13 3D models of real objects and constrain Phy3DAdvGen to generate 3D objects based on combinations of objects in this set. Extensive experiments demonstrate that our approach can generate 3D pedestrians that evade six state-of-the-art (SOTA) LiDAR 3D detectors in both CARLA simulation and physical environments, thereby highlighting vulnerabilities in safety-critical applications.

Shubo Lin, Yutong Kou, Zirui Wu et al.

While existing query-based 3D end-to-end visual trackers integrate detection and tracking via the tracking-by-attention paradigm, these two chicken-and-egg tasks encounter optimization difficulties when sharing the same parameters. Our findings reveal that these difficulties arise due to two inherent constraints on the self-attention mechanism, i.e., over-deduplication for object queries and self-centric attention for track queries. In contrast, removing the self-attention mechanism not only minimally impacts regression predictions of the tracker, but also tends to generate more latent candidate boxes. Based on these analyses, we present SynCL, a novel plug-and-play synergistic training strategy designed to co-facilitate multi-task learning for detection and tracking. Specifically, we propose a Task-specific Hybrid Matching module for a weight-shared cross-attention-based decoder that matches the targets of track queries with multiple object queries to exploit promising candidates overlooked by the self-attention mechanism. To flexibly select optimal candidates for the one-to-many matching, we also design a Dynamic Query Filtering module controlled by model training status. Moreover, we introduce Instance-aware Contrastive Learning to break through the barrier of self-centric attention for track queries, effectively bridging the gap between detection and tracking. Without additional inference costs, SynCL consistently delivers improvements in various benchmarks and achieves state-of-the-art performance with $58.9\%$ AMOTA on the nuScenes dataset. Code and raw results will be publicly available.

Mingzhe Guo, Zhipeng Zhang, Heng Fan et al.

We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perform feature matching simply using the outputs from backbone for target localization, there is no direct feedback from the matching module to the backbone network, especially the shallow layers. More concretely, only the matching module can directly access the target information (in the reference frame), while the representation learning of candidate frame is blind to the reference target. As a consequence, the accumulation effect of target-irrelevant interference in the shallow stages may degrade the feature quality of deeper layers. In this paper, we approach the problem from a different angle by conducting multiple branch-wise interactions inside the Siamese-like backbone networks (InBN). At the core of InBN is a general interaction modeler (GIM) that injects the prior knowledge of reference image to different stages of the backbone network, leading to better target-perception and robust distractor-resistance of candidate feature representation with negligible computation cost. The proposed GIM module and InBN mechanism are general and applicable to different backbone types including CNN and Transformer for improvements, as evidenced by our extensive experiments on multiple benchmarks. In particular, the CNN version (based on SiamCAR) improves the baseline with 3.2/6.9 absolute gains of SUC on LaSOT/TNL2K, respectively. The Transformer version obtains SUC scores of 65.7/52.0 on LaSOT/TNL2K, which are on par with recent state of the arts. Code and models will be released.

Jin Gao, Yan Lu, Xiaojuan Qi et al.

Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in tracking. In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training. It allows an in-built memory retention mechanism for the model to remember the knowledge about the object seen before, and thus the seen data can be safely removed from training. This also bears certain similarities to the emerging continual learning field in preventing catastrophic forgetting. This mechanism enables us to unveil the power of modern online deep trackers without incurring too much extra computational cost. We evaluate our approach based on two networks in the online learning families for tracking, i.e., multi-layer perceptrons in RT-MDNet and convolutional neural networks in DiMP. The consistent improvements on several challenging tracking benchmarks demonstrate its effectiveness and efficiency.

Minglang Qiao, Yufan Liu, Mai Xu et al.

Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition (MVVA), containing eye-tracking data and sound source annotations. Using this database, we find that sound influences human attention, and conversly attention offers a cue to determine sound source on multi-face video. Guided by these findings, a visual-audio multi-task network (VAM-Net) is introduced to predict saliency and locate sound source. VAM-Net consists of three branches corresponding to visual, audio and face modalities. Visual branch has a two-stream architecture to capture spatial and temporal information. Face and audio branches encode audio signals and faces, respectively. Finally, a spatio-temporal multi-modal graph (STMG) is constructed to model the interaction among multiple faces. With joint optimization of these branches, the intrinsic correlation of the tasks of saliency prediction and sound source localization is utilized and their performance is boosted by each other. Experiments show that the proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization.

Zekun Li, Yufan Liu, Bing Li et al.

Although transformer has achieved great progress on computer vision tasks, the scale variation in dense image prediction is still the key challenge. Few effective multi-scale techniques are applied in transformer and there are two main limitations in the current methods. On one hand, self-attention module in vanilla transformer fails to sufficiently exploit the diversity of semantic information because of its rigid mechanism. On the other hand, it is hard to build attention and interaction among different levels due to the heavy computational burden. To alleviate this problem, we first revisit multi-scale problem in dense prediction, verifying the significance of diverse semantic representation and multi-scale interaction, and exploring the adaptation of transformer to pyramidal structure. Inspired by these findings, we propose a novel Semantic-aware Decoupled Transformer Pyramid (SDTP) for dense image prediction, consisting of Intra-level Semantic Promotion (ISP), Cross-level Decoupled Interaction (CDI) and Attention Refinement Function (ARF). ISP explores the semantic diversity in different receptive space. CDI builds the global attention and interaction among different levels in decoupled space which also solves the problem of heavy computation. Besides, ARF is further added to refine the attention in transformer. Experimental results demonstrate the validity and generality of the proposed method, which outperforms the state-of-the-art by a significant margin in dense image prediction tasks. Furthermore, the proposed components are all plug-and-play, which can be embedded in other methods.

Yuxin Chen, Ziqi Zhang, Chunfeng Yuan et al.

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all channels and refining it with channel-specific correlations for each channel. Our refinement method introduces few extra parameters and significantly reduces the difficulty of modeling channel-wise topologies. Furthermore, via reformulating graph convolutions into a unified form, we find that CTR-GC relaxes strict constraints of graph convolutions, leading to stronger representation capability. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

Zhenbang Li, Yaya Shi, Jin Gao et al.

Siamese trackers are shown to be vulnerable to adversarial attacks recently. However, the existing attack methods craft the perturbations for each video independently, which comes at a non-negligible computational cost. In this paper, we show the existence of universal perturbations that can enable the targeted attack, e.g., forcing a tracker to follow the ground-truth trajectory with specified offsets, to be video-agnostic and free from inference in a network. Specifically, we attack a tracker by adding a universal imperceptible perturbation to the template image and adding a fake target, i.e., a small universal adversarial patch, into the search images adhering to the predefined trajectory, so that the tracker outputs the location and size of the fake target instead of the real target. Our approach allows perturbing a novel video to come at no additional cost except the mere addition operations -- and not require gradient optimization or network inference. Experimental results on several datasets demonstrate that our approach can effectively fool the Siamese trackers in a targeted attack manner. We show that the proposed perturbations are not only universal across videos, but also generalize well across different trackers. Such perturbations are therefore doubly universal, both with respect to the data and the network architectures. We will make our code publicly available.

Zekun Li, Yufan Liu, Bing Li et al.

Although object detection has reached a milestone thanks to the great success of deep learning, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like the classic Feature Pyramid Network (FPN) and its improvements. However, the specifically designed feature integration modules of these methods may not have the optimal architecture for feature fusion. Moreover, these models have fixed architectures and data flow paths, when fed with various samples. They cannot adjust and be compatible with each kind of data. To overcome the above limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection. It dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). ISG adaptively extracts multi-level features from backbone as the input of feature integration. CSG automatically activate informative data flow paths based on the multi-level features. Furthermore, these two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.

Ziqi Zhang, Yaya Shi, Chunfeng Yuan et al.

Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a teacher-recommended learning (TRL) method to make full use of the successful external language model (ELM) to integrate the abundant linguistic knowledge into the caption model. The ELM generates more semantically similar word proposals which extend the ground-truth words used for training to deal with the long-tailed problem. Experimental evaluations on three benchmarks: MSVD, MSR-VTT and VATEX show the proposed ORG-TRL system achieves state-of-the-art performance. Extensive ablation studies and visualizations illustrate the effectiveness of our system.

Liang Sun, Bing Li, Chunfeng Yuan et al.

Inspired by the fact that different modalities in videos carry complementary information, we propose a Multimodal Semantic Attention Network(MSAN), which is a new encoder-decoder framework incorporating multimodal semantic attributes for video captioning. In the encoding phase, we detect and generate multimodal semantic attributes by formulating it as a multi-label classification problem. Moreover, we add auxiliary classification loss to our model that can obtain more effective visual features and high-level multimodal semantic attribute distributions for sufficient video encoding. In the decoding phase, we extend each weight matrix of the conventional LSTM to an ensemble of attribute-dependent weight matrices, and employ attention mechanism to pay attention to different attributes at each time of the captioning process. We evaluate algorithm on two popular public benchmarks: MSVD and MSR-VTT, achieving competitive results with current state-of-the-art across six evaluation metrics.

Yang Du, Chunfeng Yuan, Bing Li et al.

Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local feature to obtain its weight score, which ignores interactions among local features. To address this, we propose an effective interaction-aware self-attention model inspired by PCA to learn attention maps. Furthermore, since different layers in a deep network capture feature maps of different scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps. Moreover, our spatial pyramid attention is unrestricted to the number of its input feature maps so it is easily extended to a spatio-temporal version. Finally, our model is embedded in general CNNs to form end-to-end attention networks for action classification. Experimental results show that our method achieves the state-of-the-art results on the UCF101, HMDB51 and untrimmed Charades.

Haijuan Hu, Bing Li, Quansheng Liu

We first establish a law of large numbers and a convergence theorem in distribution to show the rate of convergence of the non-local means filter for removing Gaussian noise. We then introduce the notion of degree of similarity to measure the role of similarity for the non-local means filter. Based on the convergence theorems, we propose a patch-based weighted means filter for removing impulse noise and its mixture with Gaussian noise by combining the essential idea of the trilateral filter and that of the non-local means filter. Our experiments show that our filter is competitive compared to recently proposed methods.

Bing Li, Weihua Xiong, Weiming Hu

Computational color constancy is a very important topic in computer vision and has attracted many researchers' attention. Recently, lots of research has shown the effects of high level visual content information for illumination estimation. However, all of these existing methods are essentially combinational strategies in which image's content analysis is only used to guide the combination or selection from a variety of individual illumination estimation methods. In this paper, we propose a novel bilayer sparse coding model for illumination estimation that considers image similarity in terms of both low level color distribution and high level image scene content simultaneously. For the purpose, the image's scene content information is integrated with its color distribution to obtain optimal illumination estimation model. The experimental results on two real-world image sets show that our algorithm is superior to other prevailing illumination estimation methods, even better than combinational methods.