Jianqiang Huang

Yingjie Chen, Huasong Zhong, Chong Chen et al.

Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, \ie, high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster memberships (of samples) in a probabilistic way. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which we can simply apply the standard Density Peak Clustering algorithm with a uniform threshold. Our experiments on multiple benchmarks show that each module contributes to the final performance of our method, and by incorporating them into other advanced face clustering methods, these two modules can boost the performance of these methods to a new state-of-the-art. Code is available at: https://github.com/echoanran/On-Mitigating-Hard-Clusters.

Ze Chen, Zhihang Fu, Jianqiang Huang et al.

Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention from researchers. However, most of the existing methods, which are based on multiple instance learning (MIL), tend to localize instances to the discriminative parts of salient objects instead of the entire content of all objects. In this paper, we propose a WSOD framework called the Spatial Likelihood Voting with Self-knowledge Distillation Network (SLV-SD Net). In this framework, we introduce a spatial likelihood voting (SLV) module to converge region proposal localization without bounding box annotations. Specifically, in every iteration during training, all the region proposals in a given image act as voters voting for the likelihood of each category in the spatial dimensions. After dilating the alignment on the area with large likelihood values, the voting results are regularized as bounding boxes, which are then used for the final classification and localization. Based on SLV, we further propose a self-knowledge distillation (SD) module to refine the feature representations of the given image. The likelihood maps generated by the SLV module are used to supervise the feature learning of the backbone network, encouraging the network to attend to wider and more diverse areas of the image. Extensive experiments on the PASCAL VOC 2007/2012 and MS-COCO datasets demonstrate the excellent performance of SLV-SD Net. In addition, SLV-SD Net produces new state-of-the-art results on these benchmarks.

Ze Chen, Zhihang Fu, Jianqiang Huang et al.

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent studies focus on the generation of high-quality missing annotations. In this study, we first point out that it is not enough to generate high-quality annotations using a single model, which only looks once for annotations. Through detailed experimental analyses, we further conclude that hard-label training is conducive to generating high-recall annotations, while soft-label training tends to obtain high-precision annotations. Inspired by the aspects mentioned above, we propose a dynamic supervisor framework that updates the annotations multiple times through multiple-updated submodels trained using hard and soft labels. In the final generated annotations, both recall and precision improve significantly through the integration of hard-label training with soft-label training. Extensive experiments conducted on various dataset combination settings support our analyses and demonstrate the superior performance of the proposed dynamic supervisor.

Jianqiang Huang, Jian Wang, Qianru Sun et al.

Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only foreground object parts, i.e., a lot of false negatives. An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e.g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i.e., background pixels are mistakenly included. This paper aims to tackle this issue. It proposes a new method to couple CAM and Attention matrix in a probabilistic Diffusion way, and dub it AD-CAM. Intuitively, it integrates ViT attention and CAM activation in a conservative and convincing way. Conservative is achieved by refining the attention between a pair of pixels based on their respective attentions to common neighbors, where the intuition is two pixels having very different neighborhoods are rarely dependent, i.e., their attention should be reduced. Convincing is achieved by diffusing a pixel's activation to its neighbors (on the CAM) in proportion to the corresponding attentions (on the AM). In experiments, our results on two challenging WSSS benchmarks PASCAL VOC and MS~COCO show that AD-CAM as pseudo labels can yield stronger WSSS models than the state-of-the-art variants of CAM.

Jianqiang Huang, Yu Qin, Jiaxin Qi et al.

We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck. For example, the grounding process is usually a trivial language-location association without visual reasoning, e.g., grounding any language query containing sheep to the nearly central regions, due to that most queries about sheep have ground-truth locations at the image center. First, we frame the visual grounding pipeline into a causal graph, which shows the causalities among image, query, target location and underlying confounder. Through the causal graph, we know how to break the grounding bottleneck: deconfounded visual grounding. Second, to tackle the challenge that the confounder is unobserved in general, we propose a confounder-agnostic approach called: Referring Expression Deconfounder (RED), to remove the confounding bias. Third, we implement RED as a simple language attention, which can be applied in any grounding method. On popular benchmarks, RED improves various state-of-the-art grounding methods by a significant margin. Code will soon be available at: https://github.com/JianqiangH/Deconfounded_VG.

Xin Jin, Tianyu He, Kecheng Zheng et al.

Cloth-Changing person re-identification (CC-ReID) aims at matching the same person across different locations over a long-duration, e.g., over days, and therefore inevitably meets challenge of changing clothing. In this paper, we focus on handling well the CC-ReID problem under a more challenging setting, i.e., just from a single image, which enables high-efficiency and latency-free pedestrian identify for real-time surveillance applications. Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID. GI-ReID adopts a two-stream architecture that consists of a image ReID-Stream and an auxiliary gait recognition stream (Gait-Stream). The Gait-Stream, that is discarded in the inference for high computational efficiency, acts as a regulator to encourage the ReID-Stream to capture cloth-invariant biometric motion features during the training. To get temporal continuous motion cues from a single image, we design a Gait Sequence Prediction (GSP) module for Gait-Stream to enrich gait information. Finally, a high-level semantics consistency over two streams is enforced for effective knowledge regularization. Experiments on multiple image-based Cloth-Changing ReID benchmarks, e.g., LTCC, PRCC, Real28, and VC-Clothes, demonstrate that GI-ReID performs favorably against the state-of-the-arts. Codes are available at https://github.com/jinx-USTC/GI-ReID.

Menglin Wang, Baisheng Lai, Jianqiang Huang et al.

This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseudo labels and use the produced labels to train Re-ID models progressively. These methods are relatively simple but effective. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the large intra-ID variance caused mainly by the change of camera views. To address this issue, we propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera. These camera-aware proxies enable us to deal with large intra-ID variance and generate more reliable pseudo labels for learning. Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model to effectively learn the ID discrimination ability within and across cameras. Meanwhile, a proxy-balanced sampling strategy is also designed, which facilitates our learning further. Extensive experiments on three large-scale Re-ID datasets show that our proposed approach outperforms most unsupervised methods by a significant margin. Especially, on the challenging MSMT17 dataset, we gain $14.3\%$ Rank-1 and $10.2\%$ mAP improvements when compared to the second place. Code is available at: \texttt{https://github.com/Terminator8758/CAP-master}.

Zhen Huang, Xu Shen, Xinmei Tian et al.

Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely used for this task due to their powerful capability to model graph data. The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons. Thus, previous methods mainly focus on the design/learning of the graph topology. But once the topology is learned, only a single-scale feature and one transformation exist in each layer of the networks. Many insights, such as multi-scale information and multiple sets of transformations, that have been proven to be very effective in convolutional neural networks (CNNs), have not been investigated in GCNs. The reason is that, due to the gap between graph-structured skeleton data and conventional image/video data, it is very challenging to embed these insights into GCNs. To overcome this gap, we reinvent the split-transform-merge strategy in GCNs for skeleton sequence processing. Specifically, we design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths. Extensive experiments demonstrate that our network outperforms state-of-the-art methods by a significant margin with only 1/5 of the parameters and 1/10 of the FLOPs. Code is available at https://github.com/yellowtownhz/STIGCN.

Xing Shen, Jirui Yang, Chunbo Wei et al.

Binary grid mask representation is broadly used in instance segmentation. A representative instantiation is Mask R-CNN which predicts masks on a $28\times 28$ binary grid. Generally, a low-resolution grid is not sufficient to capture the details, while a high-resolution grid dramatically increases the training complexity. In this paper, we propose a new mask representation by applying the discrete cosine transform(DCT) to encode the high-resolution binary grid mask into a compact vector. Our method, termed DCT-Mask, could be easily integrated into most pixel-based instance segmentation methods. Without any bells and whistles, DCT-Mask yields significant gains on different frameworks, backbones, datasets, and training schedules. It does not require any pre-processing or pre-training, and almost no harm to the running speed. Especially, for higher-quality annotations and more complex backbones, our method has a greater improvement. Moreover, we analyze the performance of our method from the perspective of the quality of mask representation. The main reason why DCT-Mask works well is that it obtains a high-quality mask representation with low complexity. Code is available at https://github.com/aliyun/DCT-Mask.git.

Hongwei Yong, Jianqiang Huang, Xiansheng Hua et al.

Optimization techniques are of great importance to effectively and efficiently train a deep neural network (DNN). It has been shown that using the first and second order statistics (e.g., mean and variance) to perform Z-score standardization on network activations or weight vectors, such as batch normalization (BN) and weight standardization (WS), can improve the training performance. Different from these existing methods that mostly operate on activations or weights, we present a new optimization technique, namely gradient centralization (GC), which operates directly on gradients by centralizing the gradient vectors to have zero mean. GC can be viewed as a projected gradient descent method with a constrained loss function. We show that GC can regularize both the weight space and output feature space so that it can boost the generalization performance of DNNs. Moreover, GC improves the Lipschitzness of the loss function and its gradient so that the training process becomes more efficient and stable. GC is very simple to implement and can be easily embedded into existing gradient based DNN optimizers with only one line of code. It can also be directly used to fine-tune the pre-trained DNNs. Our experiments on various applications, including general image classification, fine-grained image classification, detection and segmentation, demonstrate that GC can consistently improve the performance of DNN learning. The code of GC can be found at https://github.com/Yonghongwei/Gradient-Centralization.

Tan Wang, Jianqiang Huang, Hanwang Zhang et al.

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN.

Jiaxin Qi, Yulei Niu, Jianqiang Huang et al.

This paper unravels the design tricks adopted by us, the champion team MReaL-BDAI, for Visual Dialog Challenge 2019: two causal principles for improving Visual Dialog (VisDial). By "improving", we mean that they can promote almost every existing VisDial model to the state-of-the-art performance on the leader-board. Such a major improvement is only due to our careful inspection on the causality behind the model and data, finding that the community has overlooked two causalities in VisDial. Intuitively, Principle 1 suggests: we should remove the direct input of the dialog history to the answer model, otherwise a harmful shortcut bias will be introduced; Principle 2 says: there is an unobserved confounder for history, question, and answer, leading to spurious correlations from training data. In particular, to remove the confounder suggested in Principle 2, we propose several causal intervention algorithms, which make the training fundamentally different from the traditional likelihood estimation. Note that the two principles are model-agnostic, so they are applicable in any VisDial model. The code is available at https://github.com/simpleshinobu/visdial-principles.

Zhengxu Yu, Dong Shen, Zhongming Jin et al.

Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch. It is challenging due to the significant variations inside the target scenario, e.g., different camera viewpoint, illumination changes, and occlusion. These variations result in a gap between the distribution of each mini-batch and the whole dataset's distribution when using mini-batch training. In this paper, we study model fine-tuning from the perspective of the aggregation and utilization of the global information of the dataset when using mini-batch training. Specifically, we introduce a novel network structure called Batch-related Convolutional Cell (BConv-Cell), which progressively collects the global information of the dataset into a latent state and uses it to rectify the extracted feature. Based on BConv-Cells, we further proposed the Progressive Transfer Learning (PTL) method to facilitate the model fine-tuning process by jointly optimizing the BConv-Cells and the pre-trained ReID model. Empirical experiments show that our proposal can improve the performance of the ReID model greatly on MSMT17, Market-1501, CUHK03 and DukeMTMC-reID datasets. Moreover, we extend our proposal to the general image classification task. The experiments in several image classification benchmark datasets demonstrate that our proposal can significantly improve the performance of baseline models. The code has been released at \url{https://github.com/ZJULearning/PTL}

Zhijiang Tang, Jiaxin Qi, Yuhua Zheng et al.

Electrocardiogram~(ECG), a key bioelectrical time-series signal, is crucial for assessing cardiac health and diagnosing various diseases. Given its time-series format, ECG data is often incorporated into pre-training datasets for large-scale time-series model training. However, existing studies often overlook its unique characteristics and specialized downstream applications, which differ significantly from other time-series data, leading to an incomplete understanding of its properties. In this paper, we present an in-depth investigation of ECG signals and establish a comprehensive benchmark, which includes (1) categorizing its downstream applications into four distinct evaluation tasks, (2) identifying limitations in traditional evaluation metrics for ECG analysis, and introducing a novel metric; (3) benchmarking state-of-the-art time-series models and proposing a new architecture. Extensive experiments demonstrate that our proposed benchmark is comprehensive and robust. The results validate the effectiveness of the proposed metric and model architecture, which establish a solid foundation for advancing research in ECG signal analysis.

Jiayan Chen, Kai Li, Yulu Zhao et al.

Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model long sequences with linear complexity. In this paper, we propose EAGLE, a U-shaped network composed of a Progressive Visual State Space (PVSS) encoder and a Hybrid Visual State Space (HVSS) decoder that work collaboratively to achieve efficient and accurate segmentation of hepatic echinococcosis (HE) lesions. The proposed Convolutional Vision State Space Block (CVSSB) module is designed to fuse local and global features, while the Haar Wavelet Transformation Block (HWTB) module compresses spatial information into the channel dimension to enable lossless downsampling. Due to the lack of publicly available HE datasets, we collected CT slices from 260 patients at a local hospital. Experimental results show that EAGLE achieves state-of-the-art performance with a Dice Similarity Coefficient (DSC) of 89.76%, surpassing MSVM-UNet by 1.61%.

Wenxuan Zhang, Xuechao Zou, Li Wu et al.

Spatiotemporal prediction aims to generate future sequences by paradigms learned from historical contexts. It is essential in numerous domains, such as traffic flow prediction and weather forecasting. Recently, research in this field has been predominantly driven by deep neural networks based on autoencoder architectures. However, existing methods commonly adopt autoencoder architectures with identical receptive field sizes. To address this issue, we propose an Asymmetric Receptive Field Autoencoder (ARFA) model, which introduces corresponding sizes of receptive field modules tailored to the distinct functionalities of the encoder and decoder. In the encoder, we present a large kernel module for global spatiotemporal feature extraction. In the decoder, we develop a small kernel module for local spatiotemporal information reconstruction. Experimental results demonstrate that ARFA consistently achieves state-of-the-art performance on popular datasets. Additionally, we construct the RainBench, a large-scale radar echo dataset for precipitation prediction, to address the scarcity of meteorological data in the domain.

Deyi Ji, Haoran Wang, Mingyuan Tao et al.

Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by high-level deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillation (SSTKD) framework for semantic segmentation. Specifically, for structural texture knowledge, we introduce a Contourlet Decomposition Module (CDM) that decomposes low-level features with iterative Laplacian pyramid and directional filter bank to mine the structural texture knowledge. For statistical knowledge, we propose a Denoised Texture Intensity Equalization Module (DTIEM) to adaptively extract and enhance statistical texture knowledge through heuristics iterative quantization and denoised operation. Finally, each knowledge learning is supervised by an individual loss function, forcing the student network to mimic the teacher better from a broader perspective. Experiments show that the proposed method achieves state-of-the-art performance on Cityscapes, Pascal VOC 2012 and ADE20K datasets.

Ke Hu, Yi Qi, Jianqiang Huang et al.

Click-through rate(CTR) prediction is a core task in cost-per-click(CPC) advertising systems and has been studied extensively by machine learning practitioners. While many existing methods have been successfully deployed in practice, most of them are built upon i.i.d.(independent and identically distributed) assumption, ignoring that the click data used for training and inference is collected through time and is intrinsically non-stationary and drifting. This mismatch will inevitably lead to sub-optimal performance. To address this problem, we formulate CTR prediction as a continual learning task and propose COLF, a hybrid COntinual Learning Framework for CTR prediction, which has a memory-based modular architecture that is designed to adapt, learn and give predictions continuously when faced with non-stationary drifting click data streams. Married with a memory population method that explicitly controls the discrepancy between memory and target data, COLF is able to gain positive knowledge from its historical experience and makes improved CTR predictions. Empirical evaluations on click log collected from a major shopping app in China demonstrate our method's superiority over existing methods. Additionally, we have deployed our method online and observed significant CTR and revenue improvement, which further demonstrates our method's efficacy.

Xin Jin, Tianyu He, Xu Shen et al.

Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms. However, such clustering-based scheme becomes computationally prohibitive for large-scale datasets. How to efficiently leverage endless unlabeled data with limited computing resources for better U-ReID is under-explored. In this paper, we make the first attempt to the large-scale U-ReID and propose a "small data for big task" paradigm dubbed Meta Clustering Learning (MCL). MCL only pseudo-labels a subset of the entire unlabeled data via clustering to save computing for the first-phase training. After that, the learned cluster centroids, termed as meta-prototypes in our MCL, are regarded as a proxy annotator to softly annotate the rest unlabeled data for further polishing the model. To alleviate the potential noisy labeling issue in the polishment phase, we enforce two well-designed loss constraints to promise intra-identity consistency and inter-identity strong correlation. For multiple widely-used U-ReID benchmarks, our method significantly saves computational cost while achieving a comparable or even better performance compared to prior works.

Chao Zheng, Yingjie Chen, Chong Chen et al.

Finding a suitable density function is essential for density-based clustering algorithms such as DBSCAN and DPC. A naive density corresponding to the indicator function of a unit $d$-dimensional Euclidean ball is commonly used in these algorithms. Such density suffers from capturing local features in complex datasets. To tackle this issue, we propose a new kernel diffusion density function, which is adaptive to data of varying local distributional characteristics and smoothness. Furthermore, we develop a surrogate that can be efficiently computed in linear time and space and prove that it is asymptotically equivalent to the kernel diffusion density function. Extensive empirical experiments on benchmark and large-scale face image datasets show that the proposed approach not only achieves a significant improvement over classic density-based clustering algorithms but also outperforms the state-of-the-art face clustering methods by a large margin.

Yichen Zhu, Bo Jiang, Haiming Jin et al.

A networked time series (NETS) is a family of time series on a given graph, one for each node. It has a wide range of applications from intelligent transportation, environment monitoring to smart grid management. An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph. Most existing methods require complete data for training. However, in real-world scenarios, it is not uncommon to have missing data due to sensor malfunction, incomplete sensing coverage, etc. In this paper, we study the problem of NETS prediction with incomplete data. We propose NETS-ImpGAN, a novel deep learning framework that can be trained on incomplete data with missing values in both history and future. Furthermore, we propose Graph Temporal Attention Networks, which incorporate the attention mechanism to capture both inter-time series and temporal correlations. We conduct extensive experiments on four real-world datasets under different missing patterns and missing rates. The experimental results show that NETS-ImpGAN outperforms existing methods, reducing the MAE by up to 25%.

Zhipeng Luo, Zhixing He, Jin Wang et al.

Temporal relational data, perhaps the most commonly used data type in industrial machine learning applications, needs labor-intensive feature engineering and data analyzing for giving precise model predictions. An automatic machine learning framework is needed to ease the manual efforts in fine-tuning the models so that the experts can focus more on other problems that really need humans' engagement such as problem definition, deployment, and business services. However, there are three main challenges for building automatic solutions for temporal relational data: 1) how to effectively and automatically mining useful information from the multiple tables and the relations from them? 2) how to be self-adjustable to control the time and memory consumption within a certain budget? and 3) how to give generic solutions to a wide range of tasks? In this work, we propose our solution that successfully addresses the above issues in an end-to-end automatic way. The proposed framework, AutoSmart, is the winning solution to the KDD Cup 2019 of the AutoML Track, which is one of the largest AutoML competition to date (860 teams with around 4,955 submissions). The framework includes automatic data processing, table merging, feature engineering, and model tuning, with a time\&memory controller for efficiently and automatically formulating the models. The proposed framework outperforms the baseline solution significantly on several datasets in various domains.

Hualian Sheng, Sijia Cai, Yuan Liu et al.

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on human-designed components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerful 3D object representations. Such methods, however, have limited ability to capture rich contextual dependencies among points. In this paper, we leverage the high-quality region proposal network and a Channel-wise Transformer architecture to constitute our two-stage 3D object detection framework (CT3D) with minimal hand-crafted design. The proposed CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation for the point features within each proposal. Specifically, CT3D uses proposal's keypoints for spatial contextual modelling and learns attention propagation in the encoding module, mapping the proposal to point embeddings. Next, a new channel-wise decoding module enriches the query-key interaction via channel-wise re-weighting to effectively merge multi-level contexts, which contributes to more accurate object predictions. Extensive experiments demonstrate that our CT3D method has superior performance and excellent scalability. Remarkably, CT3D achieves the AP of 81.77% in the moderate car category on the KITTI test 3D detection benchmark, outperforms state-of-the-art 3D detectors.

Chenhang He, Jianqiang Huang, Xian-Sheng Hua et al.

Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information. Though this issue can be alleviated in a depth-based model where a depth estimation module is plugged to predict depth information before 3D box reasoning, the introduction of such module dramatically reduces the detection speed. Instead of training a costly depth estimator, we propose a rendering module to augment the training data by synthesizing images with virtual-depths. The rendering module takes as input the RGB image and its corresponding sparse depth image, outputs a variety of photo-realistic synthetic images, from which the detection model can learn more discriminative features to adapt to the depth changes of the objects. Besides, we introduce an auxiliary module to improve the detection model by jointly optimizing it through a depth estimation task. Both modules are working in the training time and no extra computation will be introduced to the detection model. Experiments show that by working with our proposed modules, a geometry-based model can represent the leading accuracy on the KITTI 3D detection benchmark.

Jianqiang Huang, Ke Hu, Qingtao Tang et al.

Click-through rate (CTR) prediction plays an important role in online advertising and recommender systems. In practice, the training of CTR models depends on click data which is intrinsically biased towards higher positions since higher position has higher CTR by nature. Existing methods such as actual position training with fixed position inference and inverse propensity weighted training with no position inference alleviate the bias problem to some extend. However, the different treatment of position information between training and inference will inevitably lead to inconsistency and sub-optimal online performance. Meanwhile, the basic assumption of these methods, i.e., the click probability is the product of examination probability and relevance probability, is oversimplified and insufficient to model the rich interaction between position and other information. In this paper, we propose a Deep Position-wise Interaction Network (DPIN) to efficiently combine all candidate items and positions for estimating CTR at each position, achieving consistency between offline and online as well as modeling the deep non-linear interaction among position, user, context and item under the limit of serving performance. Following our new treatment to the position bias in CTR prediction, we propose a new evaluation metrics named PAUC (position-wise AUC) that is suitable for measuring the ranking quality at a given position. Through extensive experiments on a real world dataset, we show empirically that our method is both effective and efficient in solving position bias problem. We have also deployed our method in production and observed statistically significant improvement over a highly optimized baseline in a rigorous A/B test.

Xiao Luo, Daqing Wu, Yiyang Gu et al.

Recent years have witnessed the explosive growth of interaction behaviors in multimedia information systems, where multi-behavior recommender systems have received increasing attention by leveraging data from various auxiliary behaviors such as tip and collect. Among various multi-behavior recommendation methods, non-sampling methods have shown superiority over negative sampling methods. However, two observations are usually ignored in existing state-of-the-art non-sampling methods based on binary regression: (1) users have different preference strengths for different items, so they cannot be measured simply by binary implicit data; (2) the dependency across multiple behaviors varies for different users and items. To tackle the above issue, we propose a novel non-sampling learning framework named Criterion-guided Heterogeneous Collaborative Filtering (CHCF). CHCF introduces both upper and lower thresholds to indicate selection criteria, which will guide user preference learning. Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction of the target behavior. We further theoretically demonstrate that the optimization of Collaborative Metric Learning can be approximately achieved by the CHCF learning framework in a non-sampling form effectively. Extensive experiments on three real-world datasets show the effectiveness of CHCF in heterogeneous scenarios.

Huasong Zhong, Jianlong Wu, Chong Chen et al.

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and clustering objective into consideration, thus the learned representations are not optimal for clustering and the performance might be limited. Towards this issue, we first propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering~(GCC) method. Different from basic contrastive clustering that only assumes an image and its augmentation should share similar representation and clustering assignments, we lift the instance-level consistency to the cluster-level consistency with the assumption that samples in one cluster and their augmentations should all be similar. Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features. On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments. Both of them incorporate the latent category information to reduce the intra-cluster variance while increasing the inter-cluster variance. Experiments on six commonly used datasets demonstrate the superiority of our proposed approach over the state-of-the-art methods.

Yuan Liu, Jingyuan Chen, Zhenfang Chen et al.

Weakly-supervised Temporal Action Localization (WTAL) aims to detect the action segments with only video-level action labels in training. The key challenge is how to distinguish the action of interest segments from the background, which is unlabelled even on the video-level. While previous works treat the background as "curses", we consider it as "blessings". Specifically, we first use causal analysis to point out that the common localization errors are due to the unobserved confounder that resides ubiquitously in visual recognition. Then, we propose a Temporal Smoothing PCA-based (TS-PCA) deconfounder, which exploits the unlabelled background to model an observed substitute for the unobserved confounder, to remove the confounding effect. Note that the proposed deconfounder is model-agnostic and non-intrusive, and hence can be applied in any WTAL method without model re-designs. Through extensive experiments on four state-of-the-art WTAL methods, we show that the deconfounder can improve all of them on the public datasets: THUMOS-14 and ActivityNet-1.3.

Tianyu He, Xin Jin, Xu Shen et al.

Video-based person re-identification (re-ID) aims at matching the same person across video clips. Efficiently exploiting multi-scale fine-grained features while building the structural interaction among them is pivotal for its success. In this paper, we propose a hybrid framework, Dense Interaction Learning (DenseIL), that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties. DenseIL contains a CNN encoder and a Dense Interaction (DI) decoder. The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames. Different from previous works, we additionally let the DI decoder densely attends to intermediate fine-grained CNN features and that naturally yields multi-grained spatial-temporal representation for each video clip. Moreover, we introduce Spatio-TEmporal Positional Embedding (STEP-Emb) into the DI decoder to investigate the positional relation among the spatial-temporal inputs. Our experiments consistently and significantly outperform all the state-of-the-art methods on multiple standard video-based person re-ID datasets.

Junyi Feng, Jiashen Hua, Baisheng Lai et al.

Model efficiency is crucial for object detection. Mostprevious works rely on either hand-crafted design or auto-search methods to obtain a static architecture, regardless ofthe difference of inputs. In this paper, we introduce a newperspective of designing efficient detectors, which is automatically generating sample-adaptive model architectureon the fly. The proposed method is named content-aware dynamic detectors (CADDet). It first applies a multi-scale densely connected network with dynamic routing as the supernet. Furthermore, we introduce a course-to-fine strat-egy tailored for object detection to guide the learning of dynamic routing, which contains two metrics: 1) dynamic global budget constraint assigns data-dependent expectedbudgets for individual samples; 2) local path similarity regularization aims to generate more diverse routing paths. With these, our method achieves higher computational efficiency while maintaining good performance. To the best of our knowledge, our CADDet is the first work to introduce dynamic routing mechanism in object detection. Experiments on MS-COCO dataset demonstrate that CADDet achieves 1.8 higher mAP with 10% fewer FLOPs compared with vanilla routing strategy. Compared with the models based upon similar building blocks, CADDet achieves a 42% FLOPs reduction with a competitive mAP.

Chaobing Shan, Chunbo Wei, Bing Deng et al.

Most of the existing tracking methods link the detected boxes to the tracklets using a linear combination of feature cosine distances and box overlap. But the problem of inconsistent features of an object in two different frames still exists. In addition, when extracting features, only appearance information is utilized, neither the location relationship nor the information of the tracklets is considered. We present an accurate and end-to-end learning framework for multi-object tracking, namely \textbf{TPAGT}. It re-extracts the features of the tracklets in the current frame based on motion predicting, which is the key to solve the problem of features inconsistent. The adaptive graph neural network in TPAGT is adopted to fuse locations, appearance, and historical information, and plays an important role in distinguishing different objects. In the training phase, we propose the balanced MSE LOSS to successfully overcome the unbalanced samples. Experiments show that our method reaches state-of-the-art performance. It achieves 76.5\% MOTA on the MOT16 challenge and 76.2\% MOTA on the MOT17 challenge.

Xiao Luo, Daqing Wu, Zeyu Ma et al.

Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure from the pre-trained model as the guiding information, i.e., treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named {\textbf{C}}omprehensive s{\textbf{I}}milarity {\textbf{M}}ining and c{\textbf{O}}nsistency lear{\textbf{N}}ing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.

Kaihua Tang, Jianqiang Huang, Hanwang Zhang

As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are long-tailed in nature; it is even impossible when the sample-of-interest co-exists with each other in one collectable unit, e.g., multiple visual instances in one image. Therefore, long-tailed classification is the key to deep learning at scale. However, existing methods are mainly based on re-weighting/re-sampling heuristics that lack a fundamental theory. In this paper, we establish a causal inference framework, which not only unravels the whys of previous methods, but also derives a new principled solution. Specifically, our theory shows that the SGD momentum is essentially a confounder in long-tailed classification. On one hand, it has a harmful causal effect that misleads the tail prediction biased towards the head. On the other hand, its induced mediation also benefits the representation learning and head prediction. Our framework elegantly disentangles the paradoxical effects of the momentum, by pursuing the direct causal effect caused by an input sample. In particular, we use causal intervention in training, and counterfactual reasoning in inference, to remove the "bad" while keep the "good". We achieve new state-of-the-arts on three long-tailed visual recognition benchmarks: Long-tailed CIFAR-10/-100, ImageNet-LT for image classification and LVIS for instance segmentation.

Zhengxu Yu, Yilun Zhao, Bin Hong et al.

With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes. All these cases can result in an inconsistent ReID performance, revealing a critical problem that current ReID models heavily rely on person's apparels. Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows. (1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. (2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparel-simulation GAN (AS-GAN) to synthesize cloth changing images according to the target cloth embedding. It's worth noting that the images used in ReID tasks were cropped from real-world low-quality CCTV videos, making it more challenging to synthesize cloth changing images. We conduct extensive experiments on several datasets comparing with several baselines. Experimental results demonstrate that our proposal can improve the ReID performance of the baseline models.

Xiao Luo, Haixin Wang, Daqing Wu et al.

Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining. Hashing is one of the most widely used methods for its computational and storage efficiency. With the development of deep learning, deep hashing methods show more advantages than traditional methods. In this survey, we detailedly investigate current deep hashing algorithms including deep supervised hashing and deep unsupervised hashing. Specifically, we categorize deep supervised hashing methods into pairwise methods, ranking-based methods, pointwise methods as well as quantization according to how measuring the similarities of the learned hash codes. Moreover, deep unsupervised hashing is categorized into similarity reconstruction-based methods, pseudo-label-based methods and prediction-free self-supervised learning-based methods based on their semantic learning manners. We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing and multi-modal deep hashing. Meanwhile, we present some commonly used public datasets and the scheme to measure the performance of deep hashing algorithms. Finally, we discuss some potential research directions in conclusion.

Kaihua Tang, Yulei Niu, Jianqiang Huang et al.

Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach". Given such SGG, the down-stream tasks such as VQA can hardly infer better scene structures than merely a bag of objects. However, debiasing in SGG is not trivial because traditional debiasing methods cannot distinguish between the good and bad bias, e.g., good context prior (e.g., "person read book" rather than "eat") and bad long-tailed bias (e.g., "near" dominating "behind / in front of"). In this paper, we present a novel SGG framework based on causal inference but not the conventional likelihood. We first build a causal graph for SGG, and perform traditional biased training with the graph. Then, we propose to draw the counterfactual causality from the trained graph to infer the effect from the bad bias, which should be removed. In particular, we use Total Direct Effect (TDE) as the proposed final predicate score for unbiased SGG. Note that our framework is agnostic to any SGG model and thus can be widely applied in the community who seeks unbiased predictions. By using the proposed Scene Graph Diagnosis toolkit on the SGG benchmark Visual Genome and several prevailing models, we observed significant improvements over the previous state-of-the-art methods.

Menglin Wang, Baisheng Lai, Haokun Chen et al.

Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view and no inter-camera identity association is labeled. It is a new setting proposed recently to reduce the burden of annotation while expect to maintain desirable Re-ID performance. However, the lack of inter-camera labels makes the ICS Re-ID problem much more challenging than the fully supervised counterpart. By investigating the characteristics of ICS, this paper proposes camera-specific non-parametric classifiers, together with a hybrid mining quintuplet loss, to perform intra-camera learning. Then, an inter-camera learning module consisting of a graph-based ID association step and a Re-ID model updating step is conducted. Extensive experiments on three large-scale Re-ID datasets show that our approach outperforms all existing ICS works by a great margin. Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.

Chuhan Wu, Fangzhao Wu, Mingxiao An et al.

News recommendation is very important to help users find interested news and alleviate information overload. Different users usually have different interests and the same user may have various interests. Thus, different users may click the same news article with attention on different aspects. In this paper, we propose a neural news recommendation model with personalized attention (NPA). The core of our approach is a news representation model and a user representation model. In the news representation model we use a CNN network to learn hidden representations of news articles based on their titles. In the user representation model we learn the representations of users based on the representations of their clicked news articles. Since different words and different news articles may have different informativeness for representing news and users, we propose to apply both word- and news-level attention mechanism to help our model attend to important words and news articles. In addition, the same news article and the same word may have different informativeness for different users. Thus, we propose a personalized attention network which exploits the embedding of user ID to generate the query vector for the word- and news-level attentions. Extensive experiments are conducted on a real-world news recommendation dataset collected from MSN news, and the results validate the effectiveness of our approach on news recommendation.

Menglin Wang, Baisheng Lai, Zhongming Jin et al.

It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deployment. How to maximally reduce the annotation cost while retaining the re-ID performance becomes an interesting problem. In this paper, we address this problem by integrating an active learning scheme into a deep learning framework. Noticing that the truly matched tracklet-pairs, also denoted as true positives (TP), are the most informative samples for our re-ID model, we propose a sampling criterion to choose the most TP-likely tracklet-pairs for annotation. A view-aware sampling strategy considering view-specific biases is designed to facilitate candidate selection, followed by an adaptive resampling step to leave out the selected candidates that are unnecessary to annotate. Our method learns the re-ID model and updates the annotation set iteratively. The re-ID model is supervised by the tracklets' pesudo labels that are initialized by treating each tracklet as a distinct class. With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model. While being simple, the proposed method demonstrates its effectiveness on three video-based person re-ID datasets. Experimental results show that less than 3\% pairwise annotations are needed for our method to reach comparable performance with the fully-supervised setting.

Ken Chen, Fei Chen, Baisheng Lai et al.

Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this paper, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio-temporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a novel graph-based spatio-temporal convolutional layer to extract features from a graph representation of traffic flows. Then several such layers are stacked together to predict future flows over time. Meanwhile, the relations between traffic flows in the graph are often time variant as the traffic condition changes over time. To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream. Experiments on real datasets demonstrate that the proposed model achieves competitive performances compared with the other state-of-the-art methods.

Wangmeng Xiang, Jianqiang Huang, Xianbiao Qi et al.

Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose. Recently, with the advancement of deep learning technologies, the performance of Person ReID has been improved swiftly. Feature extraction and feature matching are two crucial components in the training and deployment stages of Person ReID. However, many existing Person ReID methods have measure inconsistency between the training stage and the deployment stage, and they couple magnitude and orientation information of feature vectors in feature representation. Meanwhile, traditional triplet loss methods focus on samples within a mini-batch and lack knowledge of global feature distribution. To address these issues, we propose a novel homocentric hypersphere embedding scheme to decouple magnitude and orientation information for both feature and weight vectors, and reformulate classification loss and triplet loss to their angular versions and combine them into an angular discriminative loss. We evaluate our proposed method extensively on the widely used Person ReID benchmarks, including Market1501, CUHK03 and DukeMTMC-ReID. Our method demonstrates leading performance on all datasets.