Abstract
Unsupervised domain adaptation (UDA) for person re-identification (re-ID) is a challenging task due to large variations in human classes, illuminations, camera views, and so on. Currently, existing UDA methods focus on two-domain adaptation and are generally trained on one labeled source set and adapted on the other unlabeled target set. In this article, we put forward a new issue on person re-ID, namely, unsupervised multi-target domain adaptation (UMDA). It involves one labeled source set and multiple unlabeled target sets, which is more reasonable for practical real-world applications. Enabling UMDA has to learn the consistency for multiple domains, which is significantly different from the UDA problem. To ensure distribution consistency and learn the discriminative embedding, we further propose the Camera Identity-guided Distribution Consistency method that performs an alignment operation for multiple domains. The camera identities are encoded into the image semantic information to facilitate the adaptation of features. According to our knowledge, this is the first attempt on the unsupervised multi-target domain adaptation learning. Extensive experiments are executed on Market-1501, DukeMTMC-reID, MSMT17, PersonX, and CUHK03, and our method has achieved very competitive re-ID accuracy in multi-target domains against numerous state-of-the-art methods.
- Xiaobin Chang, Yongxin Yang, Tao Xiang, and Timothy M. Hospedales. 2018. Disjoint label space transfer learning with common factorised space.arXiv:1812.02605. Retrieved from https://arxiv.org/abs/1812.02605.Google Scholar
- De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. 2016. Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1335–1344.Google ScholarCross Ref
- Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2018. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8789–8797.Google ScholarCross Ref
- Jia Deng, Wei Dong, Richard Socher, Li Jia Li, Kai Li, and Fei Fei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarCross Ref
- Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, and Jianbin Jiao. 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 994–1003.Google ScholarCross Ref
- Shengyong Ding, Liang Lin, Guangrun Wang, and Hongyang Chao. 2015. Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn. 48, 10 (2015), 2993–3003. Google ScholarDigital Library
- Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Trans. Multimedia Comput. Commun. Appl. 14, 4 (2018), 83. Google ScholarDigital Library
- Pedro F. Felzenszwalb, David A. Mcallester, and Deva Ramanan. 2008. A discriminatively trained, multiscale, deformable part model. In CVPR. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarCross Ref
- Mengyue Geng, Yaowei Wang, Tao Xiang, and Yonghong Tian. 2016. Deep transfer learning for person re-identification. arXiv:1611.05244. Retrieved from https://arxiv.org/abs/1611.05244.Google Scholar
- Behnam Gholami, Pritish Sahu, Ognjen (Oggi) Rudovic, Konstantinos Bousmalis, and Vladimir Pavlovic. 2020. Unsupervised multi-target domain adaptation: An information theoretic approach. IEEE Trans. Image Process. 29 (2020), 3993–4002.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 770–778.Google ScholarCross Ref
- Fan Hehe, Zheng Liang, and Yang Yi. 2017. Unsupervised person re-identification: Clustering and fine-tuning. arXiv:1705.10444. Retrieved from https://arxiv.org/abs/1705.10444. Google ScholarDigital Library
- Alexander Hermans*, Lucas Beyer*, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv:1703.07737. Retrieved from https://arxiv.org/abs/1703.07737.Google Scholar
- Junlin Hu, Jiwen Lu, and Yap Peng Tan. 2015. Deep transfer metric learning. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15).Google ScholarCross Ref
- K. Juengling, Christoph Bodensteiner, and Michael Arens. 2011. Person re-identification in multi-camera networks. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’11). 55–61.Google ScholarCross Ref
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR’15).Google Scholar
- Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M. Roth, and Horst Bischof. 2012. Large scale metric learning from equivalence constraints. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’12). 2288–2295. Google ScholarDigital Library
- Ryan Layne, Timothy M Hospedales, and Shaogang Gong. 2012. Person re-identification by attributes. In Proceedings of the British Machine Vision Conference (BMVC’12).Google ScholarCross Ref
- Shuzhao Li, Huimin Yu, and Roland Hu. 2020. Attributes-aided part detection and refinement for person re-identification. Pattern Recogn. 97 (2020), 107016.Google ScholarDigital Library
- Wei Li, Yang Wu, and Jianqing Li. 2017. Re-identification by neighborhood structure metric learning. Pattern Recogn. 61 (2017), 327–338. Google ScholarDigital Library
- Wenjing Li and Zhongcheng Wu. 2020. OVL: One-view learning for human retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, 11410–11417.Google ScholarCross Ref
- Wei Li, Xiatian Zhu, and Shaogang Gong. 2017. Person re-identification by deep joint learning of multi-loss classification. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’17). 2194–2200. 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 IEEE Conference on Computer Vision and Pattern Recognition. 2197–2206.Google ScholarCross Ref
- Shan Lin, Haoliang Li, Chang-Tsun Li, and Alex Chichung Kot. 2018. Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. arXiv:1807.01440. Retrieved from https://arxiv.org/abs/1807.01440.Google Scholar
- Yutian Lin, Lingxi Xie, Yu Wu, Chenggang Yan, and Qi Tian. 2020. Unsupervised person re-identification via softened similarity learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
- Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, Zhilan Hu, Chenggang Yan, and Yi Yang. 2019. Improving person re-identification by attribute and identity learning. Pattern Recogn. 95 (2019), 151–161.Google ScholarDigital Library
- Omar Oreifej, Ramin Mehran, and Mubarak Shah. 2010. Human identity recognition in aerial images. In Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’10). 709–716.Google ScholarCross Ref
- V. M. Patel, R. Gopalan, R. Li, and R. Chellappa. 2015. Visual domain adaptation: An overview of recent advances. IEEE Signal Processing Magazine 32, 3 (2015), 53–69.Google ScholarCross Ref
- Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, and Yonghong Tian. 2016. Unsupervised cross-dataset transfer learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1306–1315.Google ScholarCross Ref
- Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, and Yonghong Tian. 2016. Unsupervised cross-dataset transfer learning for person re-identification. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 1306–1315.Google ScholarCross Ref
- Zhao R, Ouyang W, and Wang X. 2013. Unsupervised salience learning for person re-identification. In Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’13). 3586–3593. Google ScholarDigital Library
- Liangliang Ren, Jiwen Lu, Jianjiang Feng, and Jie Zhou. 2017. Multi-modal uniform deep learning for RGB-D person re-identification. Pattern Recognition 72 (2017), 446–457. Google ScholarDigital Library
- Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision.Google ScholarCross Ref
- Li Rui, Zhang Baopeng, Kang Dong-Joong, and Teng Zhu. 2019. Deep attention network for person re-identification with multi-loss. Comput. Electr. Eng. 79 (2019), 106455.Google ScholarCross Ref
- Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du, Qian Zhang, Chang Huang, and Xinggang Wang. 2020. Unsupervised domain adaptive re-identification: Theory and practice. Pattern Recogn. (2020), 107173.Google Scholar
- X. Sun and L. Zheng. 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19). 608–617.Google Scholar
- Andrea Vedaldi and Karel Lenc. 2015. MatConvNet - Convolutional neural networks for MATLAB. In Proceedings of the 2015 ACM Multimedia Conference (MM’15). 689–692. Google ScholarDigital Library
- Hanxiao Wang, Xiatian Zhu, Tao Xiang, and Shaogang Gong. 2016. Towards unsupervised open-set person re-identification. In Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP’16).Google ScholarCross Ref
- Jingya Wang, Xiatian Zhu, Shaogang Gong, and Wei Li. 2018. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2275–2284.Google ScholarCross Ref
- Li Wei, Zhao Rui, Xiao Tong, and X. G. Wang. 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Computer Vision and Pattern Recognition. Google ScholarDigital Library
- Longhui Wei, Shiliang Zhang, Wen Gao, and Qi Tian. 2018. Person transfer gan to bridge domain gap for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 79–88.Google ScholarCross Ref
- Longhui Wei, Shiliang Zhang, Hantao Yao, Wen Gao, and Qi Tian. 2019. GLAD: Global-local-alignment descriptor for pedestrian retrieval. IEEE Trans. Multimedia 21, 4 (2019), 986–999.Google ScholarCross Ref
- Kilian Q. Weinberger and Lawrence K. Saul. 2009. Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10, 1 (2009), 207–244. Google ScholarDigital Library
- Lin Wu, Chunhua Shen, and Anton Van Den Hengel. 2017. Deep linear discriminant analysis on fisher networks: A hybrid architecture for person re-identification. Pattern Recogn. 65 (2017), 238–250. Google ScholarDigital Library
- Lin Wu, Yang Wang, Junbin Gao, and Xue Li. 2018. Deep adaptive feature embedding with local sample distributions for person re-identification. Pattern Recogn. 73 (2018), 275–288.Google ScholarCross Ref
- Xun Yang, Meng Wang, and Dacheng Tao. [n.d.]. Person re-identification with metric learning using privileged information. (unpublished).Google Scholar
- Hong Xing Yu, Ancong Wu, and Wei Shi Zheng. 2017. Cross-view asymmetric metric learning for unsupervised person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’17).Google ScholarCross Ref
- Hong-Xing Yu, Ancong Wu, and Wei-Shi Zheng. 2017. Cross-view asymmetric metric learning for unsupervised person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 994–1002.Google ScholarCross Ref
- Hong-Xing Yu, Wei-Shi Zheng, Ancong Wu, Xiaowei Guo, Shaogang Gong, and Jian-Huang Lai. 2019. Unsupervised person re-identification by soft multilabel learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2148–2157.Google ScholarCross Ref
- Liang Zheng, Yujia Huang, Huchuan Lu, and Yi Yang. 2017. Pose invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28, 9 (2017). 4500–4509.Google ScholarCross Ref
- Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision. 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 IEEE International Conference on Computer Vision. 1116–1124. Google ScholarDigital Library
- Liang Zheng, Yi Yang, and Alexander G. Hauptmann. 2016. Person re-identification: Past, present and future. arXiv:1610.02984. Retrieved from https://arxiv.org/abs/1610.02984.Google Scholar
- Zhedong Zheng, Liang Zheng, and Yi Yang. 2016. A discriminatively learned CNN embedding for person re-identification. ACM Trans. Multimedia Comput. Commun. Appl. 14, 1 (2016). 13:1–20. Google ScholarDigital Library
- 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 IEEE International Conference on Computer Vision.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Donglin Cao, and Shaozi Li. 2017. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Shaozi Li, and Yi Yang. 2018. Generalizing a person retrieval model hetero-and homogeneously. In Proceedings of the European Conference on Computer Vision (ECCV’18). 172–188.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, and Yi Yang. 2019. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 598–607.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, and Yi Yang. 2017. Camera style adaptation for person re-identification. arXiv:1711.10295. Retrieved from https://arxiv.org/abs/1711.10295.Google Scholar
- Zhun Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, and Yi Yang. 2018. Camera style adaptation for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarCross Ref
- Qin Zhou, Shibao Zheng, Haibin Ling, Hang Su, and Shuang Wu. 2017. Joint dictionary and metric learning for person re-identification. Pattern Recogn. 72 (2017), 196–206. Google ScholarDigital Library
- Sanping Zhou, Jinjun Wang, Deyu Meng, Xiaomeng Xin, Yubing Li, Yihong Gong, and Nanning Zheng. 2018. Deep self-paced learning for person re-identification. Pattern Recogn. 76 (2018), 739–751. Google ScholarDigital Library
- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision. 2223–2232.Google ScholarCross Ref
- Xiaoke Zhu, Xiao-Yuan Jing, Fan Zhang, Xinyu Zhang, Xinge You, and Xiang Cui. 2019. Distance learning by mining hard and easy negative samples for person re-identification. Pattern Recogn. 95 (2019), 211–222.Google ScholarDigital Library
Index Terms
- A Camera Identity-guided Distribution Consistency Method for Unsupervised Multi-target Domain Person Re-identification
Recommendations
Momentum source-proxy guided initialization for unsupervised domain adaptive person re-identification
AbstractUnsupervised domain adaptive person re-identification (UDA Re-ID), aiming to adapt the model trained from source domain to target domain, is especially challenging due to the non-overlapping identities between the two Re-ID domains. ...
Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-identification
Computer Vision – ECCV 2020AbstractUnsupervised domain adaptive person Re-IDentification (ReID) is challenging because of the large domain gap between source and target domains, as well as the lackage of labeled data on the target domain. This paper tackles this challenge through ...
Unsupervised Person Re-Identification via Multi-Label Classification
AbstractThe challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. Most of previous works predict single-class pseudo labels through clustering. To improve the quality of generated pseudo ...
Comments