Junyin Zhang
ABSTRACT
Most existing cluster-based cross-domain person re-identification (re-id) methods only pre-train the re-id model on the source domain. Unfortunately, the pre-trained model may not perform well on the target domain due to the large domain gap between source and target domains, which is harmful to the following optimization. In this paper, we propose a novel Self-supervised Pre-training method on the Target Domain (SPTD), which pre-trains the model on both the source and target domains in a self-supervised manner. Specifically, SPTD uses different kinds of data augmentation manners to simulate different intra-class changes and constraints the consistency between the augmented data distribution and the original data distribution. As a result, the pre-trained model involves some specific discriminative knowledge on the target domain and is beneficial to the following optimization. It is easy to combine the proposed SPTD with other cluster-based cross-domain re-id methods just by replacing the original pre-trained model with our pre-trained model. Comprehensive experiments on three widely used datasets, i.e. Market1501, DukeMTMC-ReID and MSMT17, demonstrate the effectiveness of SPTD. Especially, the final results surpass previous state-of-the-art methods by a large margin.
- Xiaobin Chang, Yongxin Yang, Tao Xiang, and Timothy M Hospedales. 2019. Disjoint label space transfer learning with common factorised space. In Proceedings of the Artificial Intelligence. 3288--3295.Google Scholar
Cross Ref
- Peixian Chen, Pingyang Dai, Jianzhuang Liu, Feng Zheng, Qi Tian, and Rongrong Ji. 2020. Dual Distribution Alignment Network for Generalizable Person Re-Identification. arXiv:2007.13249.Google Scholar
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning. 1597--1607.Google Scholar
- 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 Computer Vision and Pattern Recognition. 994--1003.Google ScholarCross Ref
- Carl Doersch, Abhinav Gupta, and Alexei A Efros. 2015. Unsupervised visual representation learning by context prediction. In Proceedings of the International Conference on Computer Vision. 1422--1430. Google ScholarDigital Library
- Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transactions on Multimedia Computing, Communications, and Applications, 1--18. Google ScholarDigital Library
- Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, and Thomas S Huang. 2019. Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In Proceedings of the International Conference on Computer Vision. 6112--6121.Google ScholarCross Ref
- Yixiao Ge, Dapeng Chen, and Hongsheng Li. 2020. Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Reidentification. In Proceedings of the International Conference on Learning Representations.Google Scholar
- Yixiao Ge, Dapeng Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2020. Selfpaced contrastive learning with hybrid memory for domain adaptive object re-id. arXiv preprint arXiv:2006.02713.Google Scholar
- Spyros Gidaris, Praveer Singh, and Nikos Komodakis. 2018. Unsupervised representation learning by predicting image rotations. arXiv:1803.07728.Google Scholar
- Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the Computer Vision and Pattern Recognition. 9729--9738.Google ScholarCross Ref
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the Computer Vision and Pattern Recognition. 770--778.Google ScholarCross Ref
- Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv:1703.07737.Google Scholar
- Yangru Huang, Peixi Peng, Yi Jin, Junliang Xing, Congyan Lang, and Songhe Feng. 2019. Domain adaptive attention model for unsupervised cross-domain person re-identification. arXiv:1905.10529.Google Scholar
- Xin Jin, Cuiling Lan, Wenjun Zeng, and Zhibo Chen. 2020. Global distance distributions separation for unsupervised person re-identification. In Proceedings of the European Conference on Computer Vision. 735--751.Google ScholarCross Ref
- Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, and Yu-Chiang Frank Wang. 2019. Crossdataset person re-identification via unsupervised pose disentanglement and adaptation. In Proceedings of the International Conference on Computer Vision. 7919--7929.Google Scholar
- Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. 2015. Person reidentification by local maximal occurrence representation and metric learning. In Proceedings of the Computer Vision and Pattern Recognition. 2197--2206.Google Scholar
- Shengcai Liao and Ling Shao. 2019. Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. arXiv:1904.10424.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 Computer Vision and Pattern Recognition. 3390--3399.Google ScholarCross Ref
- Jiawei Liu, Zheng-Jun Zha, Di Chen, Richang Hong, and Meng Wang. 2019. Adaptive transfer network for cross-domain person re-identification. In Proceedings of the Computer Vision and Pattern Recognition. 7202--7211.Google ScholarCross Ref
- Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, and Wei Jiang. 2019. Bag of tricks and a strong baseline for deep person re-identification. In Proceedings of the Computer Vision and Pattern Recognition Workshops.Google ScholarCross Ref
- Bingpeng Ma, Yu Su, and Frederic Jurie. [n.d.]. Covariance Descriptor based on Bio-inspired Features for Person Re-identification and Face Verification. Image & Vision Computing.Google Scholar
- Mehdi Noroozi and Paolo Favaro. 2016. Unsupervised learning of visual representations by solving jigsaw puzzles. In Proceedings of the European Conference on Computer Vision. 69--84.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 Computer Vision and Pattern Recognition. 1306--1315.Google ScholarCross Ref
- 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. 17--35.Google ScholarCross Ref
- Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, and Shengjin Wang. 2018. Beyond part models: Person retrieval with refined part pooling. In Proceedings of the European Conference on Computer Vision. 480--496.Google Scholar
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t- SNE. Journal of machine learning research.Google Scholar
- Dongkai Wang and Shiliang Zhang. 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the Computer Vision and Pattern Recognition. 10981--10990.Google ScholarCross Ref
- Guangcong Wang, Jian-Huang Lai, Wenqi Liang, and Guangrun Wang. 2020. Smoothing adversarial domain attack and p-memory reconsolidation for crossdomain person re-identification. In Proceedings of the Computer Vision and Pattern Recognition. 10568--10577.Google Scholar
- 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 Computer Vision and Pattern Recognition. 2275--2284.Google ScholarCross Ref
- Menglin Wang, Baisheng Lai, Jianqiang Huang, Xiaojin Gong, and Xian-Sheng Hua. 2020. Camera-aware Proxies for Unsupervised Person Re-Identification. arXiv:2012.10674.Google Scholar
- 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 Computer Vision and Pattern Recognition. 79--88.Google ScholarCross Ref
- Ancong Wu, Wei-Shi Zheng, Xiaowei Guo, and Jian-Huang Lai. 2019. Distilled person re-identification: Towards a more scalable system. In Proceedings of the Computer Vision and Pattern Recognition. 1187--1196.Google ScholarCross Ref
- Guile Wu, Xiatian Zhu, and Shaogang Gong. 2020. Tracklet self-supervised learning for unsupervised person re-identification. In Proceedings of the Artificial Intelligence. 12362--12369.Google ScholarCross Ref
- Fengxiang Yang, Ke Li, Zhun Zhong, Zhiming Luo, Xing Sun, Hao Cheng, Xiaowei Guo, Feiyue Huang, Rongrong Ji, and Shaozi Li. 2020. Asymmetric coteaching for unsupervised cross-domain person re-identification. In Proceedings of the Artificial Intelligence. 12597--12604.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 Proceedings of the Computer Vision and Pattern Recognition. 1389--1398.Google ScholarCross Ref
- Kaiwei Zeng, Munan Ning, Yaohua Wang, and Yang Guo. 2020. Hierarchical clustering with hard-batch triplet loss for person re-identification. In Proceedings of the Computer Vision and Pattern Recognition. 13657--13665.Google ScholarCross Ref
- Yunpeng Zhai, Shijian Lu, Qixiang Ye, Xuebo Shan, Jie Chen, Rongrong Ji, and Yonghong Tian. 2020. Ad-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In Proceedings of the Computer Vision and Pattern Recognition. 9021--9030.Google ScholarCross Ref
- Yunpeng Zhai, Qixiang Ye, Shijian Lu, Mengxi Jia, Rongrong Ji, and Yonghong Tian. 2020. Multiple expert brainstorming for domain adaptive person reidentification. arXiv:2007.01546.Google Scholar
- Xinyu Zhang, Jiewei Cao, Chunhua Shen, and Mingyu You. 2019. Self training with progressive augmentation for unsupervised cross-domain person re-identification. In Proceedings of the International Conference on Computer Vision. 8222--8231.Google ScholarCross Ref
- Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Xin Jin, and Zhibo Chen. 2020. Relation-aware global attention for person re-identification. In Proceedings of the Computer Vision and Pattern Recognition. 3186--3195.Google ScholarCross Ref
- Fang Zhao, Shengcai Liao, Guo-Sen Xie, Jian Zhao, Kaihao Zhang, and Ling Shao. 2020. Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In Proceedings of the European Conference on Computer Vision. 526--544.Google ScholarCross Ref
- Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Zhizheng Zhan, and Zheng-Jun Zha. 2020. Exploiting Sample Uncertainty for Domain Adaptive Person Re- Identification. arXiv:2012.08733.Google Scholar
- Kecheng Zheng, Wu Liu, Lingxiao He, Tao Mei, Jiebo Luo, and Zheng-Jun Zha. 2021. Group-aware Label Transfer for Domain Adaptive Person Reidentification. arXiv:2103.12366 (2021).Google Scholar
- Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable person re-identification: A benchmark. In Proceedings of the International Conference on Computer Vision. 1116--1124. Google ScholarDigital Library
- 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. 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 Computer Vision and Pattern Recognition. 598--607.Google ScholarCross Ref
- Zijie Zhuang, Longhui Wei, Lingxi Xie, Tianyu Zhang, Hengheng Zhang, Haozhe Wu, Haizhou Ai, and Qi Tian. 2020. Rethinking the distribution gap of person re-identification with camera-based batch normalization. In Proceedings of the European Conference on Computer Vision. 140--157.Google ScholarDigital Library
Index Terms
- Self-Supervised Pre-training on the Target Domain for Cross-Domain Person Re-identification
Recommendations
Asymmetric Mutual Learning for Unsupervised Cross-Domain Person Re-identification
PRICAI 2021: Trends in Artificial IntelligenceAbstractUnsupervised domain adaptation in person re-identification is a challenging task. The performance of models trained on a specific domain generally degrades significantly on other domains due to the domain gaps. State-of-the-art clustering-based ...
Domain Adaptation for Speaker Verification Based on Self-supervised Learning with Adversarial Training
MultiMedia ModelingAbstractSpeaker verification models trained on a single domain have difficulty keeping performance on new domain data. Adversarial training maps different domain data to the same subspace to handle this problem. However, adversarial training only uses ...
Study of cross-domain person re-identification based on DCGAN
AbstractPerson re-identification(re-ID) techniques have been rapidly improving with the development of deep neural networks, and the accuracy of fully supervised re-ID models is already very high. However, when person re-identification models with ...
Comments