Context-Aware Graph Convolution Network for Target Re-identification

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the query and gallery sets, e.g. probe-gallery and gallery-gallery relations, thus hard samples may not be well solved due tothe limited or even misleading information. In this paper,we present a novel Context-Aware Graph Convolution Net-work (CAGCN), where the probe-gallery relations are encoded into the graph nodes and the graph edge connections are well controlled by the gallery-gallery relations. In this way, hard samples can be addressed with the context information flows among other easy samples during the graph reasoning. Specifically, we adopt an effective hard gallery sampler to obtain high recall for positive samples while keeping a reasonable graph size, which can also weaken the imbalanced problem in training process with low computation complexity. Experiments show that the proposed method achieves state-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limited overhead.

[1]  Mubarak Shah,et al.  Deep Constrained Dominant Sets for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Xu Zhao,et al.  Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization , 2018, ACCV.

[3]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Kun Wei,et al.  Lifelong Zero-Shot Learning , 2020, IJCAI.

[5]  Bing He,et al.  Part-Regularized Near-Duplicate Vehicle Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Shuang Wu,et al.  Graph Correspondence Transfer for Person Re-identification , 2018, AAAI.

[8]  Christian Poellabauer,et al.  Second-Order Non-Local Attention Networks for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[9]  Bernt Schiele,et al.  Parameter-Free Spatial Attention Network for Person Re-Identification , 2018, ArXiv.

[10]  Yu Liu,et al.  Region-based Quality Estimation Network for Large-scale Person Re-identification , 2017, AAAI.

[11]  Kaiqi Huang,et al.  Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[13]  Rainer Stiefelhagen,et al.  Person Re-identification by Deep Learning Attribute-Complementary Information , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Wei-Shi Zheng,et al.  Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Xu Zhao,et al.  Transferable Knowledge-Based Multi-Granularity Fusion Network for Weakly Supervised Temporal Action Detection , 2021, IEEE Transactions on Multimedia.

[16]  Xianglong Liu,et al.  Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[17]  Rama Chellappa,et al.  A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[18]  Yang Yang,et al.  RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Shiliang Zhang,et al.  Pose-Driven Deep Convolutional Model for Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Andrea Cavallaro,et al.  Omni-Scale Feature Learning for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Ling-Yu Duan,et al.  VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Bernard Ghanem,et al.  Can GCNs Go as Deep as CNNs? , 2019, ArXiv.

[23]  Gang Yu,et al.  High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Rongrong Ji,et al.  Salience-Guided Cascaded Suppression Network for Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Alberto Del Bimbo,et al.  Leveraging local neighborhood topology for large scale person re-identification , 2014, Pattern Recognit..

[26]  Zuozhuo Dai,et al.  Batch DropBlock Network for Person Re-Identification and Beyond , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[27]  Ming Tang,et al.  Identity-Guided Human Semantic Parsing for Person Re-Identification , 2020, ECCV.

[28]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[29]  Wei Wu,et al.  Class-wise Dynamic Graph Convolution for Semantic Segmentation , 2020, ECCV.

[30]  Jianyuan Guo,et al.  Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[31]  Shiguang Shan,et al.  Interaction-And-Aggregation Network for Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Alfredo Gardel Vicente,et al.  Person Re-Identification Ranking Optimisation by Discriminant Context Information Analysis , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[33]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[34]  Yichen Wei,et al.  Vehicle Re-Identification With Viewpoint-Aware Metric Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[35]  Wei Jiang,et al.  Bag of Tricks and a Strong Baseline for Deep Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[36]  Jian Sun,et al.  AlignedReID: Surpassing Human-Level Performance in Person Re-Identification , 2017, ArXiv.

[37]  Xiaogang Wang,et al.  Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[38]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Rongrong Ji,et al.  Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Maozhen Li,et al.  RRGCCAN: Re-Ranking via Graph Convolution Channel Attention Network for Person Re-Identification , 2020, IEEE Access.

[41]  Shengjin Wang,et al.  Linkage Based Face Clustering via Graph Convolution Network , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Xiaogang Wang,et al.  Person Re-identification with Deep Similarity-Guided Graph Neural Network , 2018, ECCV.

[43]  Weihao Gan,et al.  Challenges on Large Scale Surveillance Video Analysis , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[44]  David Zhang,et al.  Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Shuo Wang,et al.  PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[46]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[47]  Shuyuan Yang,et al.  Simple and Effective: Spatial Rescaling for Person Reidentification , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[48]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[49]  Wei Wu,et al.  BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation , 2020, AAAI.

[50]  Zhaoxiang Zhang,et al.  Spectral Feature Transformation for Person Re-Identification , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[51]  Yang Hua,et al.  Ranked List Loss for Deep Metric Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[53]  Yimin Wang,et al.  Person re-identification with content and context re-ranking , 2015, Multimedia Tools and Applications.

[54]  Rui Yu,et al.  Hard-Aware Point-to-Set Deep Metric for Person Re-identification , 2018, ECCV.

[55]  Shengcai Liao,et al.  Unsupervised Graph Association for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[56]  Yang Yang,et al.  ABD-Net: Attentive but Diverse Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[57]  Masayuki Mukunoki,et al.  Common-near-neighbor analysis for person re-identification , 2012, 2012 19th IEEE International Conference on Image Processing.

[58]  Jiwen Lu,et al.  Consistent-Aware Deep Learning for Person Re-identification in a Camera Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).