{"type":"ScholarlyArticle","title":"SafeNet: Scale-normalization and Anchor-based Feature Extraction Network for Person Re-identification","authors":[{"name":"Kun Yuan","slug":"kun-yuan","given":"Kun","family":"Yuan","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation , CAS; University of Chinese Academy of Sciences"},{"name":"Qian Zhang","slug":"qian-zhang","given":"Qian","family":"Zhang","affiliation":"Horizon Robotics"},{"name":"Chang Huang","slug":"chang-huang","given":"Chang","family":"Huang","affiliation":"Horizon Robotics"},{"name":"Shiming Xiang","slug":"shiming-xiang","given":"Shiming","family":"Xiang","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation , CAS; University of Chinese Academy of Sciences"},{"name":"Chunhong Pan","slug":"chunhong-pan","given":"Chunhong","family":"Pan","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation , CAS"}],"abstract":"Person Re-identification (ReID) is a challenging retrieval task that requires matching a person's image across non-overlapping camera views. The quality of fulfilling this task is largely determined on the robustness of the features that are used to describe the person. In this paper, we show the advantage of jointly utilizing multi-scale abstract information to learn powerful features over full body and parts. A scale normalization module is proposed to balance different scales through residual-based integration. To exploit the information hidden in non-rigid body parts, we propose an anchor-based method to capture the local contents by stacking convolutions of kernels with various aspect ratios, which focus on different spatial distributions. Finally, a well-defined framework is constructed for simultaneously learning the representations of both full body and parts. Extensive experiments conducted on current challenging large-scale person ReID datasets, including Market1501, CUHK03 and DukeMTMC, demonstrate that our proposed method achieves the state-of-the-art results.","doi":"10.24963/ijcai.2018/156","url":"https://ijcai.org/proceedings/2018/156","pdf":"https://ijcai.org/proceedings/2018/0156.pdf","markdown":"https://ijcai.org/proceedings/2018/156.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/156","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":156,"pages":{"first":1121,"last":1127},"keywords":["Machine Learning: Deep Learning","Computer Vision: Computer Vision","Machine Learning: Neural Networks","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2016] Dapeng Chen, Zejian Yuan, Badong Chen, and Nanning Zheng. Similarity learning with spatial constraints for person re-identification. In CVPR, pages 1268-1277, 2016.","title":"Similarity learning with spatial constraints for person re-identification","authors":"Dapeng Chen, Zejian Yuan, Badong Chen, Nanning Zheng","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2018] Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, and Jian-Huang Lai. Person re-identification by camera correla- tion aware feature augmentation. TPAMI, 40(2):392-408, 2018.","title":"Person re-identification by camera correlation aware feature augmentation","authors":"Ying-Cong Chen, Xiatian Zhu, Wei-Shi Zheng, Jian-Huang Lai","year":"2018","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cheng et al., 2016] De Cheng, Yihong Gong, Sanping Zhou, Jin- jun Wang, and Nanning Zheng. Person re-identification by multi- channel parts-based cnn with improved triplet loss function. In CVPR, pages 1335-1344, 2016.","title":"Person re-identification by multichannel parts-based cnn with improved triplet loss function","authors":"De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, Nanning Zheng","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Farenzena et al., 2010] Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, and Marco Cristani. Person re-identification by symmetry-driven accumulation of local features. In CVPR, pages 2360-2367, 2010.","title":"Person re-identification by symmetry-driven accumulation of local features","authors":"Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, Marco Cristani","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Geng et al., 2016] Mengyue Geng, Yaowei Wang, Tao Xiang, and Yonghong Tian. Deep transfer learning for person re- identification. arXiv preprint:1611.05244, 2016.","title":"Deep transfer learning for person reidentification","authors":"Geng","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hermans et al., 2017] Alexander Hermans, Lucas Beyer, and Bas- tian Leibe. In defense of the triplet loss for person re- identification. arXiv preprint:1703.07737, 2017.","title":"In defense of the triplet loss for person reidentification","authors":"Alexander Hermans, Lucas Beyer, Bastian Leibe","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Koestinger et al., 2012] Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, and Horst Bischof. Large scale met- ric learning from equivalence constraints. In CVPR, 2012.","title":"Large scale metric learning from equivalence constraints","authors":"Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, Horst Bischof","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kviatkovsky et al., 2013] Igor Kviatkovsky, Amit Adam, and Ehud Rivlin. Color invariants for person reidentification. TPAMI, 35(7):1622-1634, 2013.","title":"Color invariants for person reidentification","authors":"Igor Kviatkovsky, Amit Adam, Ehud Rivlin","year":"2013","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li and Wang, 2013] Wei Li and Xiaogang Wang. Locally aligned feature transforms across views. In CVPR, 2013.","title":"Locally aligned feature transforms across views","authors":"Wei Li, Xiaogang Wang","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2014] Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. Deepreid: Deep filter pairing neural network for person re- identification. In CVPR, pages 152-159, 2014.","title":"Deepreid: Deep filter pairing neural network for person reidentification","authors":"Wei Li, Rui Zhao, Tong Xiao, Xiaogang Wang","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2017a] Dangwei Li, Xiaotang Chen, Zhang Zhang, and Kaiqi Huang. Learning deep context-aware features over body and latent parts for person re-identification. In CVPR, 2017.","title":"Learning deep context-aware features over body and latent parts for person re-identification","authors":"Li","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2017b] Wei Li, Xiatian Zhu, and Shaogang Gong. Person re-identification by deep joint learning of multi-loss classifica- tion. IJCAI, pages 770-778, 2017.","title":"Person re-identification by deep joint learning of multi-loss classification","authors":"Li","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/305"},{"position":14,"raw":"[Liao and Li, 2015] Shengcai Liao and Stan Z Li. Efficient psd con- strained asymmetric metric learning for person re-identification. In ICCV, pages 3685-3693, 2015.","title":"Efficient psd constrained asymmetric metric learning for person re-identification","authors":"Li ; Liao, Shengcai Liao, Stan Z Li","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liao et al., 2015] Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. Person re-identification by local maximal occurrence representation and metric learning. In CVPR, 2015.","title":"Person re-identification by local maximal occurrence representation and metric learning","authors":"Shengcai Liao, Yang Hu, Xiangyu Zhu, Stan Z Li","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lin et al., 2017a] Ji Lin, Liangliang Ren, Jiwen Lu, Jianjiang Feng, and Jie Zhou. Consistent-aware deep learning for person re-identification in a camera network. In CVPR, volume 6, 2017.","title":"Consistent-aware deep learning for person re-identification in a camera network","authors":"Lin","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lin et al., 2017b] Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, and Yi Yang. Improving person re-identification by at- tribute and identity learning. arXiv preprint:1703.07220, 2017.","title":"Improving person re-identification by attribute and identity learning","authors":"Lin","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Navon, 1977] David Navon. Forest before trees: The precedence of global features in visual perception. CP, 9(3):353-383, 1977.","title":"Forest before trees: The precedence of global features in visual perception","authors":"David Navon","year":"1977","venue":"CP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Qian et al., 2017] Xuelin Qian, Yanwei Fu, Yu-Gang Jiang, Tao Xiang, and Xiangyang Xue. Multi-scale deep learning architec- tures for person re-identification. ICCV, 2017.","title":"Multi-scale deep learning architectures for person re-identification","authors":"Xuelin Qian, Yanwei Fu, Yu-Gang Jiang, Tao Xiang, Xiangyang Xue","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ristani et al., 2016] Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. Performance measures and a data set for multi-target, multi-camera tracking. In ECCV, pages 17-35, 2016.","title":"Performance measures and a data set for multi-target, multi-camera tracking","authors":"Ristani","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Schumann and Stiefelhagen, 2017] Arne Schumann and Rainer Stiefelhagen. Person re-identification by deep learning attribute- complementary information. In CVPR Workshop, 2017.","title":"Person re-identification by deep learning attributecomplementary information","authors":"Stiefelhagen Schumann, Arne Schumann, Rainer Stiefelhagen","year":"2017","venue":"CVPR Workshop","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Shi et al., 2016] Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, and Stan Z Li. Embedding deep metric for person re-identification: A study against large varia- tions. In ECCV, pages 732-748, 2016.","title":"Embedding deep metric for person re-identification: A study against large variations","authors":"Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, Stan Z Li","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sun et al., 2017] Yifan Sun, Liang Zheng, Weijian Deng, and Shengjin Wang. Svdnet for pedestrian retrieval. In ICCV, pages 3820-3828, 2017.","title":"Svdnet for pedestrian retrieval","authors":"Yifan Sun, Liang Zheng, Weijian Deng, Shengjin Wang","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Theunissen et al., 2001] F. E. Theunissen, S. V. David, N. C. Singh, A Hsu, W. E. Vinje, and J. L. Gallant. Estimating spatio- temporal receptive fields of auditory and visual neurons from their responses to natural stimuli. NCNS, 12(3):289-316, 2001.","title":"Estimating spatiotemporal receptive fields of auditory and visual neurons from their responses to natural stimuli","authors":"F E Theunissen, S V David, N C Singh, W E Hsu, J L Vinje, Gallant","year":"2001","venue":"NCNS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Varior et al., 2016] Rahul Rama Varior, Mrinal Haloi, and Gang Wang. Gated siamese convolutional neural network architecture for human re-identification. In ECCV, pages 791-808, 2016.","title":"Gated siamese convolutional neural network architecture for human re-identification","authors":"Rahul Rama Varior, Mrinal Haloi, Gang Wang","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2014] Jiang Wang, Yang Song, Thomas Leung, Chuck Rosenberg, Jingbin Wang, James Philbin, Bo Chen, and Ying Wu. Learning fine-grained image similarity with deep rank- ing. In ICCV, pages 1386-1393, 2014.","title":"Learning fine-grained image similarity with deep ranking","authors":"Jiang Wang, Yang Song, Thomas Leung, Chuck Rosenberg, Jingbin Wang, James Philbin, Bo Chen, Ying Wu","year":"2014","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xiao et al., 2016] Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. Learning deep feature representations with do- main guided dropout for person re-identification. In ICCV, pages 1249-1258, 2016.","title":"Learning deep feature representations with domain guided dropout for person re-identification","authors":"Tong Xiao, Hongsheng Li, Wanli Ouyang, Xiaogang Wang","year":"2016","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2016a] Li Zhang, Tao Xiang, and Shaogang Gong. Learning a discriminative null space for person re-identification. In CVPR, pages 1239-1248, 2016.","title":"Learning a discriminative null space for person re-identification","authors":"Zhang","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2016b] Ying Zhang, Baohua Li, Huchuan Lu, At- shushi Irie, and Xiang Ruan. Sample-specific svm learning for person re-identification. In CVPR, pages 1278-1287, 2016.","title":"Sample-specific svm learning for person re-identification","authors":"Zhang","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zheng et al., 2013] Wei-Shi Zheng, Shaogang Gong, and Tao Xi- ang. Reidentification by relative distance comparison. TPAMI, 35(3):653-668, 2013.","title":"Reidentification by relative distance comparison","authors":"Wei-Shi Zheng, Shaogang Gong, Tao Xiang","year":"2013","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zheng et al., 2015] Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. Scalable person re- identification: A benchmark. In ICCV, pages 1116-1124, 2015.","title":"Scalable person reidentification: A benchmark","authors":"Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, Qi Tian","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zheng et al., 2016] Liang Zheng, Zhi Bie, Yifan Sun, Jingdong Wang, Chi Su, Shengjin Wang, and Qi Tian. Mars: A video benchmark for large-scale person re-identification. In ECCV, pages 868-884, 2016.","title":"Mars: A video benchmark for large-scale person re-identification","authors":"Liang Zheng, Zhi Bie, Yifan Sun, Jingdong Wang, Chi Su, Shengjin Wang, Qi Tian","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zheng et al., 2017a] Zhedong Zheng, Liang Zheng, and Yi Yang. Pedestrian alignment network for large-scale person re- identification. arXiv preprint:1707.00408, 2017.","title":"Pedestrian alignment network for large-scale person reidentification","authors":"Zheng","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zheng et al., 2017b] Zhedong Zheng, Liang Zheng, and Yi Yang. Unlabeled samples generated by gan improve the person re- identification baseline in vitro. In ICCV, 2017.","title":"Unlabeled samples generated by gan improve the person reidentification baseline in vitro","authors":"Zheng","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhou et al., 2017a] Jiahuan Zhou, Pei Yu, Wei Tang, and Ying Wu. Efficient online local metric adaptation via negative samples for person re-identification. In CVPR, 2017.","title":"Efficient online local metric adaptation via negative samples for person re-identification","authors":"Zhou","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou et al., 2017b] Sanping Zhou, Jinjun Wang, Jiayun Wang, Yi- hong Gong, and Nanning Zheng. Point to set similarity based deep feature learning for person re-identification. In CVPR, vol- ume 6, 2017.","title":"Point to set similarity based deep feature learning for person re-identification","authors":"Zhou","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}