Cited By
View all- Du HLi JCao LHao X(2025)Progressive de-preference task-specific processing for generalizable person re-identificationKnowledge-Based Systems10.1016/j.knosys.2024.112779309(112779)Online publication date: Jan-2025
Style Variable and Irrelevant Learning for Generalizable Person Re-identification
Authors: 
Kai Lv, Haobo Chen, Chuyang Zhao, Kai Tu, Junru Chen, Yadong Li, Boxun Li, Youfang LinAuthors Info & Claims
Article No.: 281, Pages 1 - 22
Abstract
Domain generalization person re-identification (DG-ReID) has gained much attention recently due to the poor performance of supervised re-identification on unseen domains. The goal of domain generalization is to develop a model that is insensitive to domain bias and can perform well across different domains. In this article, We conduct experiments to verify the importance of style factors in domain bias. Specifically, the experiments are to affirm that style bias across different domains significantly contributes to domain bias. Based on this observation, we propose style variable and irrelevant learning (SVIL) to eliminate the influence of style factors on the model. Specifically, we employ a style jitter module (SJM) that enhances the style diversity of a specific source domain and reduces the style differences among various source domains. This allows the model to focus on identity-relevant information and be robust to style changes. We also integrate the SJM module with a meta-learning algorithm to further enhance the model’s generalization ability. Notably, our SJM module is easy to implement and does not add any inference cost. Our extensive experiments demonstrate the effectiveness of our approach, which outperforms existing methods on DG-ReID benchmarks.
References
[1]
Yan Bai, Jile Jiao, Ce Wang, Jun Liu, Yihang Lou, Xuetao Feng, and Ling-Yu Duan. 2021. Person30K: A dual-meta generalization network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2123–2132.
[2]
Yogesh Balaji, Swami Sankaranarayanan, and Rama Chellappa. 2018. MetaReg: Towards domain generalization using meta-regularization. In Proceedings of the Advances in Neural Information Processing Systems. 1006–1016.
[3]
Seokeon Choi, Taekyung Kim, Minki Jeong, Hyoungseob Park, and Changick Kim. 2021. meta batch-instance normalization for generalizable person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3425–3435.
[4]
Ruihang Chu, Yifan Sun, Yadong Li, Zheng Liu, Chi Zhang, and Yichen Wei. 2019. vehicle re-identification with viewpoint-aware metric learning. In Proceedings of the International Conference on Computer Vision. 8281–8290.
[5]
Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, and Ling-Yu Duan. 2021. Generalizable person re-identification with relevance-aware mixture of experts. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 16145–16154.
[6]
Yuhang Ding, Hehe Fan, Mingliang Xu, and Yi Yang. 2020. Adaptive exploration for unsupervised person re-identification. ACM Transactions on Multimedia Computing, Communications and Applications 16, 1 (2020), 3:1–3:19.
[7]
Vincent Dumoulin, Jonathon Shlens, and Manjunath Kudlur. 2016. A learned representation for artistic style. In Proceedings of the International Conference on Learning Representations.
[8]
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 14, 4 (2018), 83:1–83:18.
[9]
Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the International Conference on Machine Learning. 1126–1135.
[10]
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 IEEE Conference on Computer Vision and Pattern Recognition. 6112–6121.
[11]
Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2016. Image style transfer using convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2414–2423.
[12]
Yixiao Ge, Dapeng Chen, and Hongsheng Li. 2020. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In Proceedings of the International Conference on Learning Representations.
[13]
Douglas Gray and Hai Tao. 2008. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Proceedings of the European Conference on Computer Vision. Springer, 262–275.
[14]
Guangxing Han, Xuan Zhang, and Chongrong Li. 2023. One-shot unsupervised cross-domain person re-identification. IEEE Transactions on Circuits and Systems for Video Technology 34, 3 (2023), 1339–1351.
[15]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.
[16]
Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang. 2021. TransReID: transformer-based object re-identification. In Proceedings of the International Conference on Computer Vision. 14993–15002.
[17]
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
[18]
Martin Hirzer, Csaba Beleznai, Peter M. Roth, and Horst Bischof. 2011. Person re-identification by descriptive and discriminative classification. In Proceedings of the Scandinavian Conference on Image Analysis. Springer, 91–102.
[19]
Xiaobo Hu, Youfang Lin, Shuo Wang, Zhihao Wu, and Kai Lv. 2023. Agent-centric relation graph for object visual navigation. IEEE Transactions on Circuits and Systems for Video Technology 34, 2 (2023), 1295–1309.
[20]
Xun Huang and Serge Belongie. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the International Conference on Computer Vision. 1501–1510.
[21]
Jieru Jia, Qiuqi Ruan, and Timothy M. Hospedales. 2019. Frustratingly easy person re-identification: Generalizing person re-ID in practice. In Proceedings of the British Machine Vision Conference. 117.
[22]
Xin Jin, Tianyu He, Kecheng Zheng, Zhiheng Yin, Xu Shen, Zhen Huang, Ruoyu Feng, Jianqiang Huang, Zhibo Chen, and Xian-Sheng Hua. 2022. Cloth-changing person re-identification from a single image with gait prediction and regularization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 14258–14267.
[23]
Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen, and Li Zhang. 2020. Style normalization and restitution for generalizable person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3143–3152.
[24]
Sultan Daud Khan and Habib Ullah. 2019. A survey of advances in vision-based vehicle re-identification. Computer Vision and Image Understanding 182 (2019), 50–63.
[25]
Devinder Kumar, Parthipan Siva, Paul Marchwica, and Alexander Wong. 2020. Unsupervised domain adaptation in person re-ID via k-reciprocal clustering and large-scale heterogeneous environment synthesis. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision. 2645–2654.
[26]
Chuan Li and Michael Wand. 2016. Combining Markov random fields and convolutional neural networks for image synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2479–2486.
[27]
Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M Hospedales. 2018b. Learning to generalize: Meta-learning for domain generalization. In Proceedings of the AAAI Conference on Artificial Intelligence. 3490–3497.
[28]
Haoliang Li, Sinno Jialin Pan, Shiqi Wang, and Alex C. Kot. 2018a. Domain generalization with adversarial feature learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5400–5409.
[29]
Wei Li and Xiaogang Wang. 2013. Locally aligned feature transforms across views. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3594–3601.
[30]
Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 152–159.
[31]
Yuke Li, Jingkuan Song, Hao Ni, and Heng Tao Shen. 2023. Style-controllable generalized person re-identification. In Proceedings of the ACM International Conference on Multimedia. 7912–7921.
[32]
Yanghao Li, Naiyan Wang, Jiaying Liu, and Xiaodi Hou. 2017. Demystifying neural style transfer. In Proceedings of the International Joint Conference on Artificial Intelligence. 2230–2236.
[33]
Shengcai Liao and Ling Shao. 2019. Interpretable and generalizable deep image matching with adaptive convolutions. arXiv:1904.10424. Retrieved from https://arxiv.org/abs/1904.10424
[34]
Shengcai Liao and Ling Shao. 2020. Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In Proceedings of the European Conference on Computer Vision. Springer, 456–474.
[35]
Shan Lin, Chang-Tsun Li, and Alex C. Kot. 2020. Multi-domain adversarial feature generalization for person re-identification. IEEE Transactions on Image Processing 30 (2020), 1596–1607.
[36]
Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, and Errui Ding. 2021. AdaAttN: revisit attention mechanism in arbitrary neural style transfer. In Proceedings of the International Conference on Computer Vision. 6629–6638.
[37]
Xiaobin Liu, Shiliang Zhang, Qingming Huang, and Wen Gao. 2018. RAM: A region-aware deep model for vehicle re-identification. In Proceedings of the International Conference on Multimedia and Expo. 1–6.
[38]
Chen Change Loy, Tao Xiang, and Shaogang Gong. 2010. Time-delayed correlation analysis for multi-camera activity understanding. International Journal of Computer Vision 90, 1 (2010), 106–129.
[39]
Kai Lv, Heming Du, Yunzhong Hou, Weijian Deng, Hao Sheng, Jianbin Jiao, and Liang Zheng. 2019. vehicle re-identification with location and time stamps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 399–406.
[40]
Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, and Liang Zheng. 2020. Improving driver gaze prediction with reinforced attention. IEEE Transactions on Multimedia 23 (2020), 4198–4207.
[41]
Kai Lv, Shuo Wang, Shuai Han, and Youfang Lin. 2023. Spatially-regularized features for vehicle re-identification: An explanation of where deep models should focus. IEEE Transactions on Intelligent Transportation Systems 24, 12 (2023), 14010–14021.
[42]
Krikamol Muandet, David Balduzzi, and Bernhard Schölkopf. 2013. Domain generalization via invariant feature representation. In Proceedings of the International Conference on Machine Learning. 10–18.
[43]
Xingang Pan, Ping Luo, Jianping Shi, and Xiaoou Tang. 2018. Two at once: Enhancing learning and generalization capacities via ibn-net. In Proceedings of the European Conference on Computer Vision. 464–479.
[44]
Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, and Michael S. Lew. 2021. Lifelong person re-identification via adaptive knowledge accumulation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7901–7910.
[45]
Nan Pu, Yu Liu, Wei Chen, Erwin M. Bakker, and Michael S. Lew. 2022. Meta reconciliation normalization for lifelong person re-identification. In Proceedings of the ACM International Conference on Multimedia. 541–549.
[46]
Nan Pu, Zhun Zhong, Nicu Sebe, and Michael S. Lew. 2023. A memorizing and generalizing framework for lifelong person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 11 (2023), 13567–13585.
[47]
Lei Qi, Lei Wang, Yinghuan Shi, and Xin Geng. 2023. A novel mix-normalization method for generalizable multi-source person re-identification. IEEE Transactions on Multimedia 25 (2022), 4856–4867.
[48]
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 International Conference on Computer Vision. 5409–5418.
[49]
Ergys Ristani, Francesco Solera, Roger S. 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 Workshop, Vol. 9914. 17–35.
[50]
Shiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, and Sunita Sarawagi. 2018. Generalizing across domains via cross-gradient training. In Proceedings of the International Conference on Learning Representations.
[51]
Hao Sheng, Kai Lv, Yang Liu, Wei Ke, Weifeng Lyu, Zhang Xiong, and Wei Li. 2020. Combining pose invariant and discriminative features for vehicle reidentification. IEEE Internet of Things Journal 8, 5 (2020), 3189–3200.
[52]
Jifei Song, Yongxin Yang, Yi-Zhe Song, Tao Xiang, and Timothy M Hospedales. 2019. Generalizable person re-identification by domain-invariant mapping network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 719–728.
[53]
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 Recognition 102 (2020), 107173.
[54]
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 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6397–6406.
[55]
Masato Tamura and Tomokazu Murakami. 2019. Augmented hard example mining for generalizable person re-identification. arXiv:1910.05280. Retrieved from https://arxiv.org/abs/1910.05280
[56]
Wentao Tan, Changxing Ding, Pengfei Wang, Mingming Gong, and Kui Jia. 2023. Style interleaved learning for generalizable person re-identification. IEEE Transactions on Multimedia 26 (2023), 1600–1612.
[57]
Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, and Dimitris Metaxas. 2021. CrossNorm and SelfNorm for generalization under distribution shifts. In Proceedings of the International Conference on Computer Vision. 52–61.
[58]
Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2017. Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6924–6932.
[59]
Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008). 2579–2605.
[60]
Feng Wang, Xiang Xiang, Jian Cheng, and Alan Loddon Yuille. 2017. NormFace: L\({}_{2}\) Hypersphere Embedding for Face Verification. In Proceedings of the ACM International Conference on Multimedia. 1041–1049.
[61]
Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. 2018. CosFace: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5265–5274.
[62]
Shuo Wang, Zhihao Wu, Xiaobo Hu, Youfang Lin, and Kai Lv. 2023. Skill-based hierarchical reinforcement learning for target visual navigation. IEEE Transactions on Multimedia 25 (2023), 8920–8932.
[63]
Zhikang Wang, Lihuo He, Xiaoguang Tu, Jian Zhao, Xinbo Gao, Shengmei Shen, and Jiashi Feng. 2021. Robust video-based person re-identification by hierarchical mining. IEEE Transactions on Circuits and Systems for Video Technology 32, 12 (2021), 8179–8191.
[64]
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.
[65]
Lin Wu, Chunhua Shen, and Anton van den Hengel. 2016. PersonNet: person re-identification with deep convolutional neural networks. arXiv:1601.07255. Retrieved from https://arxiv.org/abs/1601.07255
[66]
Tong Xiao, Shuang Li, Bochao Wang, Liang Lin, and Xiaogang Wang. 2017. Joint detection and identification feature learning for person search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3415–3424.
[67]
Boqiang Xu, Jian Liang, Lingxiao He, and Zhenan Sun. 2022. Mimic embedding via adaptive aggregation: learning generalizable person re-identification. In Proceedings of the European Conference on Computer Vision. Springer, 372–388.
[68]
Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, and Steven CH Hoi. 2021. Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 6 (2021), 2872–2893.
[69]
Shijie Yu, Feng Zhu, Dapeng Chen, Rui Zhao, Haobin Chen, Shixiang Tang, Jinguo Zhu, and Yu Qiao. 2021. Multiple domain experts collaborative learning: Multi-source domain generalization for person re-identification. arXiv:2105.12355. Retrieved from https://arxiv.org/abs/2105.12355
[70]
Lei Zhang, Zhipu Liu, Wensheng Zhang, and David Zhang. 2023. Style uncertainty based self-paced meta learning for generalizable person re-identification. IEEE Transactions on Image Processing 32 (2023), 2107–2119.
[71]
Yuyang Zhao, Zhun Zhong, Fengxiang Yang, Zhiming Luo, Yaojin Lin, Shaozi Li, and Nicu Sebe. 2021. Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6277–6286.
[72]
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.
[73]
Wei-Shi Zheng, Shaogang Gong, and Tao Xiang. 2009. Associating groups of people. In Proceedings of the British Machine Vision Conference, Vol. 2. 1–11.
[74]
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 International Conference on Computer Vision. 3754–3762.
[75]
Xian Zhong, Tianyou Lu, Wenxin Huang, Mang Ye, Xuemei Jia, and Chia-Wen Lin. 2021. Grayscale enhancement colorization network for visible-infrared person re-identification. IEEE Transactions on Circuits and Systems for Video Technology 32, 3 (2021), 1418–1430.
[76]
Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, and Tao Xiang. 2019. Omni-scale feature learning for person re-identification. In Proceedings of the International Conference on Computer Vision. 3702–3712.
[77]
Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, and Tao Xiang. 2021a. Learning generalisable omni-scale representations for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 5056–5069.
[78]
Kaiyang Zhou, Yongxin Yang, Timothy M. Hospedales, and Tao Xiang. 2020. Learning to generate novel domains for domain generalization. In Proceedings of the European Conference on Computer Vision, Vol. 12361. 561–578.
[79]
Kaiyang Zhou, Yongxin Yang, Yu Qiao, and Tao Xiang. 2021b. Domain generalization with mixstyle. In Proceedings of the International Conference on Learning Representations.
Index Terms
- Style Variable and Irrelevant Learning for Generalizable Person Re-identification
Recommendations
Style-Controllable Generalized Person Re-identification
MM '23: Proceedings of the 31st ACM International Conference on MultimediaDomain generalizable person Re-identification is a challenging and realistic task. It requires a model to train on multi-source domains and then generalizes well on unseen target domains. Existing approaches typically mix images from different domains in ...
Rethinking Normalization Layers for Domain Generalizable Person Re-identification
Computer Vision – ECCV 2024AbstractDomain Generalizable Person Re-Identification (DG-ReID) strives to transfer learned feature representation from source domains to unseen target domains, despite significant distribution shifts. While most existing methods enhance model ...
Style Elimination and Information Restitution for generalizable person re-identification
AbstractDomain generalizable person re-identification (DG ReID) aims to obtain a model that can be applied directly to unseen domains once trained on a set of source domains (datasets collected from different camera networks). Among current DG ReID ...
Highlights- A Style Elimination and Information Restitution module for handling domain bias.
- An optimization strategy for improving the generalization ability.
- We propose a framework for generalizable person re-identification.
- Significant ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2024
780 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 23 September 2024
Online AM: 06 June 2024
Accepted: 25 May 2024
Revised: 08 May 2024
Received: 18 January 2024
Published in TOMM Volume 20, Issue 9
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 142Total Downloads
- Downloads (Last 12 months)142
- Downloads (Last 6 weeks)21
Reflects downloads up to 06 Jan 2025
Other Metrics
Citations
Cited By
View all- Du HLi JCao LHao X(2025)Progressive de-preference task-specific processing for generalizable person re-identificationKnowledge-Based Systems10.1016/j.knosys.2024.112779309(112779)Online publication date: Jan-2025
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in