Abstract
In this article, we propose a novel deep Siamese architecture based on a convolutional neural network (CNN) and multi-level similarity perception for the person re-identification (re-ID) problem. According to the distinct characteristics of diverse feature maps, we effectively apply different similarity constraints to both low-level and high-level feature maps during training stage. Due to the introduction of appropriate similarity comparison mechanisms at different levels, the proposed approach can adaptively learn discriminative local and global feature representations, respectively, while the former is more sensitive in localizing part-level prominent patterns relevant to re-identifying people across cameras. Meanwhile, a novel strong activation pooling strategy is utilized on the last convolutional layer for abstract local-feature aggregation to pursue more representative feature representations. Based on this, we propose final feature embedding by simultaneously encoding original global features and discriminative local features. In addition, our framework has two other benefits: First, classification constraints can be easily incorporated into the framework, forming a unified multi-task network with similarity constraints. Second, as similarity-comparable information has been encoded in the network’s learning parameters via back-propagation, pairwise input is not necessary at test time. That means we can extract features of each gallery image and build an index in an off-line manner, which is essential for large-scale real-world applications. Experimental results on multiple challenging benchmarks demonstrate that our method achieves splendid performance compared with the current state-of-the-art approaches.
- Ejaz Ahmed, Michael Jones, and Tim K. Marks. 2015. An improved deep learning architecture for person re-identification. In Proceedings of the CVPR.Google Scholar
- Léon Bottou. 2012. Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade. Springer, 421--436.Google Scholar
- Xiaobin Chang, Timothy M. Hospedales, and Tao Xiang. 2018. Multi-level factorisation net for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Dapeng Chen, Zejian Yuan, Badong Chen, and Nanning Zheng. 2016b. Similarity learning with spatial constraints for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Dapeng Chen, Zejian Yuan, Gang Hua, Nanning Zheng, and Jingdong Wang. 2015a. Similarity learning on an explicit polynomial kernel feature map for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Weihua Chen, Xiaotang Chen, Jianguo Zhang, and Kaiqi Huang. 2016a. A multi-task deep network for person re-identification. Retrieved from arXiv preprint arXiv:1607.05369 (2016). Google ScholarDigital Library
- Ying-Cong Chen, Wei-Shi Zheng, and Jianhuang Lai. 2015b. Mirror representation for modeling view-specific transform in person re-identification. In Proceedings of the IJCAI. Google ScholarDigital Library
- Sumit Chopra, Raia Hadsell, and Yann LeCun. 2005. Learning a similarity metric discriminatively, with application to face verification. In Proceedings of the CVPR. Google ScholarDigital Library
- Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, and Marco Cristani. 2010. Person re-identification by symmetry-driven accumulation of local features. In Proceedings of the CVPR.Google ScholarCross Ref
- Niloofar Gheissari, Thomas B. Sebastian, and Richard Hartley. 2006. Person reidentification using spatiotemporal appearance. In Proceedings of the CVPR. Google ScholarDigital Library
- Ross Girshick. 2015. Fast R-CNN. In Proceedings of the ICCV. Google ScholarDigital Library
- Matthieu Guillaumin, Jakob Verbeek, and Cordelia Schmid. 2009. Is that you? Metric learning approaches for face identification. In Proceedings of the ICCV.Google ScholarCross Ref
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the ICML. Google ScholarDigital Library
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the ACM-MM. Google ScholarDigital Library
- Cijo Jose and François Fleuret. 2016. Scalable metric learning via weighted approximate rank component analysis. In Proceedings of the ECCV.Google ScholarCross Ref
- Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M. Roth, and Horst Bischof. 2012. Large scale metric learning from equivalence constraints. In Proceedings of the CVPR. Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the NIPS. Google ScholarDigital Library
- Sheng Li, Ming Shao, and Yun Fu. 2015. Cross-view projective dictionary learning for person re-identification. In Proceedings of the IJCAI. Google ScholarDigital Library
- Wei Li, Rui Zhao, and Xiaogang Wang. 2012. Human reidentification with transferred metric learning. In Proceedings of the ACCV. Google ScholarDigital Library
- Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. 2014. Deepreid: Deep filter pairing neural network for person re-identification. In Proceedings of the CVPR. Google ScholarDigital Library
- Wei Li, Xiatian Zhu, and Shaogang Gong. 2017. Person re-identification by deep joint learning of multi-loss classification. In Proceedings of the IJCAI. Google ScholarDigital Library
- Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z. Li. 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the CVPR.Google Scholar
- Shengcai Liao and Stan Z. Li. 2015. Efficient PSD constrained asymmetric metric learning for person re-identification. In Proceedings of the ICCV. Google ScholarDigital Library
- Xiaokai Liu, Hongyu Wang, Yi Wu, Jimei Yang, and Ming-Hsuan Yang. 2015. An ensemble color model for human re-identification. In Proceedings of the WACV. Google ScholarDigital Library
- Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, and Yoichi Sato. 2016. Hierarchical Gaussian descriptor for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Alexis Mignon and Frédéric Jurie. 2012. PCCA: A new approach for distance learning from sparse pairwise constraints. In Proceedings of the CVPR. Google ScholarDigital Library
- Hyeonjoon Moon and P. Jonathon Phillips. 2001. Computational and performance aspects of PCA-based face-recognition algorithms. Perception 30, 3 (2001), 303--321.Google ScholarCross Ref
- Sakrapee Paisitkriangkrai, Chunhua Shen, and Anton van den Hengel. 2015. Learning to rank in person re-identification with metric ensembles. In Proceedings of the CVPR.Google Scholar
- Sateesh Pedagadi, James Orwell, Sergio Velastin, and Boghos Boghossian. 2013. Local fisher discriminant analysis for pedestrian re-identification. In Proceedings of the CVPR. Google ScholarDigital Library
- Bryan Prosser, Wei-Shi Zheng, Shaogang Gong, Tao Xiang, and Q. Mary. 2010. Person re-identification by support vector ranking. In Proceedings of the BMVC.Google Scholar
- Xuelin Qian, Yanwei Fu, Yu-Gang Jiang, Tao Xiang, and Xiangyang Xue. 2017. Multi-scale deep learning architectures for person re-identification. In Proceedings of the ICCV.Google ScholarCross Ref
- Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the CVPR.Google ScholarCross Ref
- Chen Shen, Zhongming Jin, Yiru Zhao, Zhihang Fu, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua. 2017a. Deep Siamese network with multi-level similarity perception for person re-identification. In Proceedings of the ACM-MM. ACM, 1942--1950. Google ScholarDigital Library
- Chen Shen, Chang Zhou, Zhongming Jin, Wenqing Chu, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua. 2017b. Learning feature embedding with strong neural activations for fine-grained retrieval. In Proceedings of the ACM-MM Thematic Workshops. Google ScholarDigital Library
- Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, and Stan Z. Li. 2016. Embedding deep metric for person re-identification: A study against large variations. In Proceedings of the ECCV.Google Scholar
- Zhiyuan Shi, Timothy M. Hospedales, and Tao Xiang. 2015. Transferring a semantic representation for person re-identification and search. In Proceedings of the CVPR.Google ScholarCross Ref
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. Retrieved from arXiv preprint arXiv:1409.1556.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 Proceedings of the ICCV.Google ScholarCross Ref
- Arulkumar Subramaniam, Moitreya Chatterjee, and Anurag Mittal. 2016. Deep neural networks with inexact matching for person re-identification. In Proceedings of the NIPS. Google ScholarDigital Library
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the CVPR.Google ScholarCross Ref
- Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision. In Proceedings of the CVPR.Google ScholarCross Ref
- Rahul Rama Varior, Mrinal Haloi, and Gang Wang. 2016. Gated Siamese convolutional neural network architecture for human re-identification. In Proceedings of the ECCV.Google ScholarCross Ref
- Faqiang Wang, Wangmeng Zuo, Liang Lin, David Zhang, and Lei Zhang. 2016b. Joint learning of single-image and cross-image representations for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, and Heng Tao Shen. 2016a. A survey on learning to hash. Retrieved from arXiv preprint arXiv:1606.00185.Google Scholar
- Kilian Q. Weinberger, John Blitzer, and Lawrence Saul. 2006. Distance metric learning for large margin nearest neighbor classification. In Proceedings of the NIPS. Google ScholarDigital Library
- Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. 2016. Learning deep feature representations with domain guided dropout for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Fei Xiong, Mengran Gou, Octavia Camps, and Mario Sznaier. 2014. Person re-identification using kernel-based metric learning methods. In Proceedings of the ECCV.Google ScholarCross Ref
- Yang Yang, Shengcai Liao, Zhen Lei, and Stan Z Li. 2016. Large scale similarity learning using similar pairs for person verification. In Proceedings of the AAAI. Google ScholarDigital Library
- Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. 2014. Deep metric learning for person re-identification. In Proceedings of the ICPR. Google ScholarDigital Library
- Li Zhang, Tao Xiang, and Shaogang Gong. 2016b. Learning a discriminative null space for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Ying Zhang, Baohua Li, Huchuan Lu, Atshushi Irie, and Xiang Ruan. 2016a. Sample-specific SVM learning for person re-identification. In Proceedings of the CVPR.Google ScholarCross Ref
- Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, and Xiaoou Tang. 2017. Spindle net: Person re-identification with human body region guided feature decomposition and fusion. In Proceedings of the CVPR.Google ScholarCross Ref
- Rui Zhao, Wanli Ouyang, and Xiaogang Wang. 2013. Person re-identification by salience matching. In Proceedings of the ICCV. Google ScholarDigital Library
- Rui Zhao, Wanli Ouyang, and Xiaogang Wang. 2014. Learning mid-level filters for person re-identification. In Proceedings of the CVPR. Google ScholarDigital Library
- Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable person re-identification: A benchmark. In Proceedings of the ICCV. Google ScholarDigital Library
- Liang Zheng, Yi Yang, and Alexander G. Hauptmann. 2016a. Person re-identification: Past, present and future. Retrieved from arXiv preprint arXiv:1610.02984.Google Scholar
- Liang Zheng, Yi Yang, and Qi Tian. 2016b. SIFT meets CNN: A decade survey of instance retrieval. Retrieved from arXiv preprint arXiv:1608.01807.Google Scholar
- Zhedong Zheng, Liang Zheng, and Yi Yang. 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the ICCV.Google ScholarCross Ref
Index Terms
- Multi-level Similarity Perception Network for Person Re-identification
Recommendations
Deep Siamese Network with Multi-level Similarity Perception for Person Re-identification
MM '17: Proceedings of the 25th ACM international conference on MultimediaPerson re-identification (re-ID), which aims at spotting a person of interest across multiple camera views, has gained more and more attention in computer vision community. In this paper, we propose a novel deep Siamese architecture based on ...
Multi-view feature fusion for person re-identification
AbstractPerson re-identification (ReID) suffers from camera view variants. Existing works, which typically learn a feature for each image, share a limitation that the learned features are single-view: each feature only contains information in ...
Highlights- The complementary-view features are defined to mitigate view bias.
- Multi-view ...
Graphical abstractDisplay Omitted
Part-based Feature Extraction for Person Re-identification
ICMLC '18: Proceedings of the 2018 10th International Conference on Machine Learning and ComputingIn this paper, we propose a new part-based CNN feature extraction method for end-to-end person re-identification. In our method, the input images are first divided into two different non-overlapping parts, and then two different CNN models are trained ...
Comments