ABSTRACT
Person re-identification (ReID) aims to match detected pedestrian images from multiple non-overlapping cameras. Most existing methods employ a backbone CNN to extract a vectorized feature representation by performing some global pooling operations (such as global average pooling and global max pooling) on the 3D feature map (i.e., the output of the backbone CNN). Although simple and effective in some situations, the global pooling operation only focuses on the statistical properties and ignores the spatial distribution of the feature map. Hence, it can not distinguish two feature maps when they have similar response values located in totally different positions. To handle this challenge, a novel method is proposed to learn the discriminative spatial features. Firstly, a self-constrained spatial transformer network (SC-STN) is introduced to handle the misalignments caused by detection errors. Then, based on the prior knowledge that the spatial structure of a pedestrian often keeps robust in vertical orientation of images, a novel vertical convolution network (VCN) is proposed to extract the spatial feature in vertical. Extensive experimental evaluations on several benchmarks demonstrate that the proposed method achieves state-of-the-art performances by introducing only a few parameters to the backbone.
Supplemental Material
- Leulseged Tesfaye Alemu, Marcello Pelillo, and Mubarak Shah. 2019. Deep Constrained Dominant Sets for Person Re-Identification. In ICCV.Google Scholar
- Xiaobin Chang, Timothy M. Hospedales, and Tao Xiang. 2018. Multi-Level Factorisation Net for Person Re-Identification. In CVPR.Google Scholar
- Binghui Chen, Weihong Deng, and Jiani Hu. 2019 a. Mixed High-Order Attention Network for Person Re-Identification. In ICCV.Google Scholar
- Dapeng Chen, Dan Xu, Hongsheng Li, Nicu Sebe, and Xiaogang Wang. 2018. Group Consistent Similarity Learning via Deep CRF for Person Re-Identification. In CVPR.Google Scholar
- Dapeng Chen, Zejian Yuan, Gang Hua, Nanning Zheng, and Jingdong Wang. 2015. Similarity learning on an explicit polynomial kernel feature map for person re-identification. In CVPR.Google Scholar
- Guangyi Chen, Chunze Lin, Liangliang Ren, Jiwen Lu, and Jie Zhou. 2019 c. Self-Critical Attention Learning for Person Re-Identification. In ICCV.Google Scholar
- Guangyi Chen, Tianren Zhang, Jiwen Lu, and Jie Zhou. 2019 d. Deep Meta Metric Learning. In ICCV.Google Scholar
- Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, and Zhangyang Wang. 2019 b. ABD-Net: Attentive but Diverse Person Re-Identification. In ICCV.Google Scholar
- Weihua Chen, Xiaotang Chen, Jianguo Zhang, and Kaiqi Huang. 2017. Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-Identification. In CVPR.Google Scholar
- Yifan Chen, Han Wang, Xiaolu Sun, Bin Fan, and Chu Tang. 2020. Deep Attention Aware Feature Learning for Person Re-Identification. arxiv: 2003.00517 [cs.CV]Google Scholar
- Francois Chollet. 2017. Xception: Deep Learning With Depthwise Separable Convolutions. In CVPR.Google Scholar
- Zuozhuo Dai, Mingqiang Chen, Xiaodong Gu, Siyu Zhu, and Ping Tan. 2019. Batch DropBlock Network for Person Re-Identification and Beyond. In ICCV.Google Scholar
- Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, and Fei Fei Li. 2009. ImageNet: a Large-Scale Hierarchical Image Database. In CVPR.Google Scholar
- Xing Fan, Wei Jiang, Hao Luo, and Mengjuan Fei. 2019. SphereReID: Deep hypersphere manifold embedding for person re-identification. Visual Communication and Image Representation, Vol. 60 (2019), 51--58.Google ScholarCross Ref
- P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. 2010. Object Detection with Discriminatively Trained Part-Based Models. TPAMI, Vol. 32, 9 (2010), 1627--1645.Google ScholarDigital Library
- Yang Fu, Yunchao Wei, Yuqian Zhou, Honghui Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, and Thomas Huang. 2019. Horizontal Pyramid Matching for Person Re-Identification. In AAAI.Google Scholar
- Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, and Hongsheng Li. 2018. FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification. In NeurIPS.Google Scholar
- Shaogang Gong, Marco Cristani, Change Loy Chen, and Timothy M. Hospedales. 2014. The Re-identification Challenge. Springer London. 1--20 pages.Google Scholar
- Douglas Gray and Tao Hai. 2008. Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features. In ECCV.Google Scholar
- Jianyuan Guo, Yuhui Yuan, Lang Huang, Chao Zhang, Jin-Ge Yao, and Kai Han. 2019. Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification. In ICCV.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR.Google Scholar
- Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In Defense of the Triplet Loss for Person Re-Identification. ArXiv preprint arXiv:1703.07737 (2017).Google Scholar
- Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, and Xilin Chen. 2019. Interaction-And-Aggregation Network for Person Re-Identification. In CVPR.Google Scholar
- Houjing Huang, Dangwei Li, Zhang Zhang, Xiaotang Chen, and Kaiqi Huang. 2018. Adversarially Occluded Samples for Person Re-Identification. In CVPR.Google Scholar
- Max Jaderberg, Karen Simonyan, Andrew Zisserman, and koray kavukcuoglu. 2015. Spatial Transformer Networks. In NeurIPS.Google Scholar
- Mahdi M. Kalayeh, Emrah Basaran, Muhittin Gokmen, Mustafa E. Kamasak, and Mubarak Shah. 2018. Human Semantic Parsing for Person Re-Identification. In CVPR.Google Scholar
- Dangwei Li, Xiaotang Chen, Zhang Zhang, and Kaiqi Huang. 2017. Learning Deep Context-Aware Features Over Body and Latent Parts for Person Re-Identification. In CVPR.Google Scholar
- Yan Li, Junge Zhang, Jianguo Zhang, and Kaiqi Huang. 2018. Discriminative Learning of Latent Features for Zero-Shot Recognition. In CVPR.Google Scholar
- Tsung Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Dollár. 2014. Microsoft COCO: Common Objects in Context. In CVPR.Google Scholar
- Fangyi Liu and Lei Zhang. 2019. View Confusion Feature Learning for Person Re-Identification. In ICCV.Google Scholar
- Chuanchen Luo, Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang. 2019 a. Spectral Feature Transformation for Person Re-Identification. In ICCV.Google Scholar
- Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, and Wei Jiang. 2019 b. Bag of Tricks and A Strong Baseline for Deep Person Re-identification. In CVPR Workshop.Google Scholar
- Xuelin Qian, Yanwei Fu, Tao Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, and Xiangyang Xue. 2018. Pose-Normalized Image Generation for Person Re-identification. In ECCV.Google Scholar
- Ruijie Quan, Xuanyi Dong, Yu Wu, Linchao Zhu, and Yi Yang. 2019. Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification. In ICCV.Google Scholar
- Youngmin Ro, Jongwon Choi, Dae Ung Jo, Byeongho Heo, Jongin Lim, and Jin Young Choi. 2019. Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification. In AAAI.Google Scholar
- Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In CVPR.Google Scholar
- Yantao Shen, Hongsheng Li, Tong Xiao, Shuai Yi, Dapeng Chen, and Xiaogang Wang. 2018a. Deep Group-Shuffling Random Walk for Person Re-Identification. In CVPR.Google Scholar
- Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, and Xiaogang Wang. 2018b. End-to-End Deep Kronecker-Product Matching for Person Re-Identification. In CVPR.Google Scholar
- Chi Su, Jianing Li, Shiliang Zhang, Junliang Xing, Wen Gao, and Qi Tian. 2017. Pose-Driven Deep Convolutional Model for Person Re-Identification. In ICCV.Google Scholar
- Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, and Kyoung Mu Lee. 2018. Part-Aligned Bilinear Representations for Person Re-Identification. In ECCV.Google Scholar
- Han Sun, Zhiyuan Chen, Shiyang Yan, and Lin Xu. 2019. MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-Identification. In ICCV.Google Scholar
- Yifan Sun, Changmao Cheng, Yuhan Zhang, Chi Zhang, Liang Zheng, Zhongdao Wang, and Yichen Wei. 2020. Circle Loss: A Unified Perspective of Pair Similarity Optimization. In CVPR.Google Scholar
- Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, and Shengjin Wang. 2018. Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline). In ECCV.Google Scholar
- Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. 2016. Rethinking the Inception Architecture for Computer Vision. In CVPR.Google Scholar
- Rahman Tanzila, Rochan Mrigank, and Wang Yang. 2017. Person Re-Identification by Localizing Discriminative Regions. In BMVC.Google Scholar
- Chiat-Pin Tay, Sharmili Roy, and Kim-Hui Yap. 2019. AANet: Attribute Attention Network for Person Re-Identifications. In CVPR.Google Scholar
- Maoqing Tian, Shuai Yi, Hongsheng Li, Shihua Li, Xuesen Zhang, Jianping Shi, Junjie Yan, and Xiaogang Wang. 2018. Eliminating Background-Bias for Robust Person Re-Identification. In CVPR.Google Scholar
- Cheng Wang, Qian Zhang, Chang Huang, Wenyu Liu, and Xinggang Wang. 2018c. Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification. In ECCV.Google Scholar
- Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, and Xi Zhou. 2018b. Learning Discriminative Features with Multiple Granularities for Person Re-Identification. In ACM MM.Google Scholar
- Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, and Neil M. Robertson. 2019. Ranked List Loss for Deep Metric Learning. In CVPR.Google Scholar
- Yicheng Wang, Zhenzhong Chen, Feng Wu, and Gang Wang. 2018a. Person Re-Identification With Cascaded Pairwise Convolutions. In CVPR.Google Scholar
- Longhui Wei, Shiliang Zhang, Wen Gao, and Qi Tian. 2018. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification. In CVPR.Google Scholar
- Bryan (Ning) Xia, Yuan Gong, Yizhe Zhang, and Christian Poellabauer. 2019. Second-Order Non-Local Attention Networks for Person Re-Identification. In ICCV.Google Scholar
- Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. 2016. Learning Deep Feature Representations With Domain Guided Dropout for Person Re-Identification. In CVPR.Google Scholar
- Tong Xiao, Shuang Li, Bochao Wang, Liang Lin, and Xiaogang Wang. 2017. Joint Detection and Identification Feature Learning for Person Search. In CVPR.Google Scholar
- Jing Xu, Rui Zhao, Feng Zhu, Huaming Wang, and Wanli Ouyang. 2018. Attention-Aware Compositional Network for Person Re-Identification. In CVPR.Google Scholar
- Jiwei Yang, Xu Shen, Xinmei Tian, Houqiang Li, Jianqiang Huang, and XianSheng Hua. 2018. Local Convolutional Neural Networks for Person Re-Identification. In ACM MM.Google Scholar
- Wenjie Yang, Houjing Huang, Zhang Zhang, Xiaotang Chen, Kaiqi Huang, and Shu Zhang. 2019. Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification. In CVPR.Google Scholar
- Fisher Yu, Vladlen Koltun, and Thomas Funkhouser. 2017. Dilated Residual Networks. In CVPR.Google Scholar
- Xuan Zhang, Hao Luo, Xing Fan, Weilai Xiang, Yixiao Sun, Qiqi Xiao, Wei Jiang, Chi Zhang, and Jian Sun. 2017. AlignedReID: Surpassing Human-Level Performance in Person Re-Identification. arXiv preprint arXiv:1711.08184 (2017).Google Scholar
- Yaqing Zhang, Xi Li, and Zhongfei Zhang. 2019 b. Learning a Key-Value Memory Co-Attention Matching Network for Person Re-Identification. In AAAI.Google Scholar
- Ying Zhang, Tao Xiang, Timothy M. Hospedales, and Huchuan Lu. 2018. Deep Mutual Learning. In CVPR.Google Scholar
- Yingying Zhang, Qiaoyong Zhong, Liang Ma, Di Xie, and Shiliang Pu. 2019 c. Learning Incremental Triplet Margin for Person Re-Identification. In AAAI.Google Scholar
- Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, and Zhibo Chen. 2019 a. Densely Semantically Aligned Person Re-Identification. In CVPR.Google Scholar
- Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Xin Jin, and Zhibo Chen. 2020. Relation-Aware Global Attention for Person Re-identification. In CVPR.Google Scholar
- Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, and Xiaoou Tang. 2017b. Spindle Net: Person Re-Identification With Human Body Region Guided Feature Decomposition and Fusion. In CVPR.Google Scholar
- Liming Zhao, Xi Li, Yueting Zhuang, and Jingdong Wang. 2017a. Deeply-Learned Part-Aligned Representations for Person Re-Identification. In ICCV.Google Scholar
- Feng Zheng, Cheng Deng, Xing Sun, Xinyang Jiang, Xiaowei Guo, Zongqiao Yu, Feiyue Huang, and Rongrong Ji. 2019 a. Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training. In CVPR.Google Scholar
- Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable Person Re-identification: A Benchmark. In ICCV.Google Scholar
- Liang Zheng, Yi Yang, and Alexander G Hauptmann. 2016. Person Re-identification: Past, Present and Future. ArXiv preprint arXiv:1610.02984 (2016).Google Scholar
- Meng Zheng, Srikrishna Karanam, Ziyan Wu, and Richard J. Radke. 2019 b. Re-Identification With Consistent Attentive Siamese Networks. In CVPR.Google Scholar
- Zhedong Zheng, Xiaodong Yang, Zhiding Yu, Liang Zheng, Yi Yang, and Jan Kautz. 2019 c. Joint Discriminative and Generative Learning for Person Re-Identification. In CVPR.Google Scholar
- Zhedong Zheng, Liang Zheng, and Yi Yang. 2017. Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro. In ICCV.Google Scholar
- Z. Zheng, L. Zheng, and Y. Yang. 2019. Pedestrian Alignment Network for Large-scale Person Re-Identification. IEEE TCSVT, Vol. 29, 10 (2019), 3037--3045.Google Scholar
- Zhun Zhong, Liang Zheng, Donglin Cao, and Shaozi Li. 2017a. Re-Ranking Person Re-Identification With k-Reciprocal Encoding. In CVPR.Google Scholar
- Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, and Yi Yang. 2017b. Random Erasing Data Augmentation. ArXiv preprint arXiv:1708.04896 (2017).Google Scholar
- Zhun Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, and Yi Yang. 2018. Camera Style Adaptation for Person Re-Identification. In CVPR.Google Scholar
- Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, and Tao Xiang. 2019 b. Omni-Scale Feature Learning for Person Re-Identification. In ICCV.Google Scholar
- Qinqin Zhou, Bineng Zhong, Xiangyuan Lan, Gan Sun, Yulun Zhang, and Mengran Gou. 2019 c. LRDNN: Local-refining based Deep Neural Network for Person Re-Identification with Attribute Discerning. In IJCAI.Google Scholar
- Sanping Zhou, Fei Wang, Zeyi Huang, and Jinjun Wang. 2019 a. Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification. In ICCV.Google Scholar
Index Terms
- Discriminative Spatial Feature Learning for Person Re-Identification
Recommendations
Domain-invariant feature extraction and fusion for cross-domain person re-identification
AbstractThere are notable style differences among person re-identification (ReID) datasets, such as brightness, tone, resolution, background, and clothing style, that result in serious challenges for cross-domain person ReID. Two methods are usually used ...
Person re-identification with features-based clustering and deep features
AbstractPerson re-identification (ReID) is an imperative area of pedestrian analysis and has practical applications in visual surveillance. In the person ReID, the robust feature representation is a key issue because of inconsistent visual appearances of ...
Efficient relation extraction method based on spatial feature using ELM
Entity relation extraction can be applied in the automatic question answering system, digital library and many other fields. However, the previous works on this topic mainly focused on the features from a sentence itself in the data sets, without ...
Comments