Mutual purification for unsupervised domain adaptation in person re-identification
Authors: 
Lei Zhang, Qishuai Diao, Na Jiang, Zhong Zhou, Wei WuAuthors Info & Claims
Pages 16929 - 16944
Abstract
Unsupervised domain adaptation person re-identification aims to adapt the model learned on a labeled source domain to an unlabeled target domain. It has attracted extensively attention in the computer vision community due to its important applications in security and surveillance. Existing approaches are primary to utilize pseudo labels assigned by clustering algorithm as supervision information on target domain. One of the most successful methods exploits neighbors of each unlabeled image to generate pseudo labels, in which contain noise and errors inevitably. In this paper, we propose a Mutual Purification Network (MP-Net) to alleviate errors of pseudo-labels and errors accumulation. MP-Net aims to utilize two independent pre-trained models to learn external auxiliary knowledge from each other, which consists of mutual purification neighbors-exploiting (MPNE) and mutual purification selection (MPS). MPNE focuses on using the common and unique knowledge of the two models to mine more robust neighbor relationships for alleviating the noise and errors from the normal neighbors exploiting. MPS aims to filter outliers and construct reliable triplets during training with triplet loss in unsupervised scenario. Each model selects more reliable and informative positives and negatives for peer models based on dynamic ranking and isolation computation. Extensive experiments on three large-scale public datasets, including Market-1501, DukeMTMC and MSMT17 illustrate that our MP-Net outperforms or shows comparable results to the state-of-the-art methods.
References
[1]
Wang Z, Hu R, Yu Y, Jiang J, Liang C, and Wang J Scale-adaptive low-resolution person re-identification via learning a discriminating surface IJCAI 2016 2 6
[2]
Bedagkar-Gala A and Shah SK A survey of approaches and trends in person re-identification Image Vis Comput 2014 32 4 270-286
[3]
Vezzani R, Baltieri D, and Cucchiara R People reidentification in surveillance and forensics: a survey ACM Comput Surv (CSUR) 2013 46 2 1-37
[4]
Deng W, Zheng L, Ye Q, Kang G, Yang Y, Jiao J (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. pp 994–1003
[5]
Zou Y, Yang X, Yu Z, Kumar BVK, Kautz J (2020) Joint disentangling and adaptation for cross-domain person re-identification. arXiv preprint arXiv:2007.10315
[6]
Fu Y, Wei Y, Wang G, Zhou Y, Shi H, Huang TS (2019) Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: Proceedings of the IEEE international conference on computer Vision. pp 6112–6121
[7]
Zhai Y, Lu S, Ye Q, Shan X, Chen J, Ji R, Tian Y (2020) Ad-cluster: augmented discriminative clustering for domain adaptive person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 9021–9030
[8]
Zhu X, Li Y, Sun J, Chen H, and Zhu J Learning with noisy labels method for unsupervised domain adaptive person re-identification Neurocomputing 2021 452 78-88
[9]
Zhong Z, Zheng L, Li S, Yang Y (2018) Generalizing a person retrieval model hetero-and homogeneously. In: Proceedings of the european conference on computer vision (ECCV). pp 172–188
[10]
Liu J, Zha ZJ, Chen D, Hong R, Wang M (2019) Adaptive transfer network for cross-domain person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 7202–7211
[11]
Zhang Y, Xiang T, Hospedales TM, Lu H (2018) Deep mutual learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4320–4328
[12]
Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1318–1327
[13]
Song L, Wang C, Zhang L, Du B, Zhang Q, Huang C, and Wang X Unsupervised domain adaptive re-identification: theory and practice Pattern Recogn 2020 102
[14]
Zhang X, Cao J, Shen C, You M (2019) Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: Proceedings of the IEEE international conference on computer vision. pp 8222–8231
[15]
Han B, Yao Q, Yu X, Niu G, Xu M, Hu W, Tsang I, Sugiyama M (2018) Co-teaching: robust training of deep neural networks with extremely noisy labels. Adv Neural Inf Process Syst 8527–8537
[16]
Zhao F, Liao S, Xie GS, Zhao J, Zhang K, Shao L (2020) Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In: European conference on computer vision. Springer, pp 526–544
[17]
Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Proceedings of the IEEE international conference on computer vision. pp 1116–1124
[18]
Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: European conference on computer vision. Springer, pp 17–35
[19]
Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 79–88
[20]
Fu D, Chen D, Bao J, Yang H, Yuan L, Zhang L, Li H, Chen D (2021) Unsupervised pre-training for person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 14750–14759
[21]
Ning X, Gong K, Li W, Zhang L, Bai X, and Tian S Feature refinement and filter network for person re-identification IEEE Trans Circuits Syst Video Technol 2020 31 9 3391-3402
[22]
Yi D, Lei Z, Liao S, Li SZ (2014) Deep metric learning for person re-identification. In: 2014 22nd international conference on pattern recognition. IEEE, pp 34–39
[23]
Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 152–159
[24]
Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984
[25]
Imani Z and Soltanizadeh H Histogram of the node strength and histogram of the edge weight: two new features for rgb-d person re-identification Sci China Inf Sci 2018 61 9 1-14
[26]
Su C, Li J, Zhang S, Xing J, Gao W, Tian Q (2017) Pose-driven deep convolutional model for person re-identification. In: Proceedings of the IEEE international conference on computer vision. pp 3960–3969
[27]
Yan C, Pang G, Bai X, Liu C, Xin N, Gu L, Zhou J (2021) Beyond triplet loss: person re-identification with fine-grained difference-aware pairwise loss. IEEE Trans Multimed
[28]
Zhang L, Xiang T, Gong S (2016) Learning a discriminative null space for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1239–1248
[29]
Yan Y, Ni B, Song Z, Ma C, Yan Y, Yang X (2016) Person re-identification via recurrent feature aggregation. In: European conference on computer vision. Springer, pp 701–716
[30]
Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: Proceedings of the IEEE international conference on computer vision. pp 3754–3762
[31]
Zheng Z, Zheng L, and Yang Y A discriminatively learned cnn embedding for person reidentification ACM Trans Multimed Comput Commun Appl (TOMM) 2017 14 1 1-20
[32]
Varior RR, Shuai B, Lu J, Xu D, Wang G (2016) A siamese long short-term memory architecture for human re-identification. In: European conference on computer vision. Springer, pp 135–153
[33]
Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 7167–7176
[34]
Huang H, Yang W, Chen X, Zhao X, Huang K, Lin J, Huang G, Du D (2018) Eanet: enhancing alignment for cross-domain person re-identification. arXiv preprint arXiv:1812.11369
[35]
Song J, Yang Y, Song YZ, Xiang T, Hospedales TM (2019) Generalizable person re-identification by domain-invariant mapping network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 719–728
[36]
Wang J, Zhu X, Gong S, Li W (2018) Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 2275–2284
[37]
Li YJ, Lin CS, Lin YB, Wang YCF (2019) Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision. pp 7919–7929
[38]
Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 598–607
[39]
Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2020) Learning to adapt invariance in memory for person re-identification. IEEE Trans Pattern Anal Mach Intell
[40]
Qi L, Wang L, Huo J, Zhou L, Shi Y, Gao Y (2019) A novel unsupervised camera-aware domain adaptation framework for person re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision. pp 8080–8089
[41]
Sun J, Li Y, Chen H, Peng Y, and Zhu J Unsupervised cross domain person re-identification by multi-loss optimization learning IEEE Trans Image Process 2021 30 2935-2946
[42]
Feng H, Chen M, Jinming H, Shen D, Liu H, and Cai D Complementary pseudo labels for unsupervised domain adaptation on person re-identification IEEE Trans Image Process 2021 30 2898-2907
[43]
Yu X, Han B, Yao J, Niu G, Tsang I, Sugiyama M (2019) How does disagreement help generalization against label corruption? In: International conference on machine learning. PMLR, pp 7164–7173
[44]
Patrini G, Rozza A, Menon AK, Nock R, Qu L (2017) Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1944–1952
[45]
Malach E, Shalev-Shwartz S (2017)Decoupling“when to update”from“how to update”. Adv Neural Inf Process Syst 30
[46]
Wu Y, Lin Y, Dong X, Yan Y, Ouyang W, Yang Y (2018) Exploit the unknown gradually: one-shot video-based person re-identification by stepwise learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 5177–5186
[47]
Wu Y, Lin Y, Dong X, Yan Y, Bian W, and Yang Y Progressive learning for person re-identification with one example IEEE Trans Image Process 2019 28 6 2872-2881
[48]
Ge Y, Chen D, Li H (2020) Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv preprint arXiv:2001.01526
[49]
Yang, Li K, Zhong Z, Luo Z, Sun X, Cheng H, Guo X, Huang F, Ji R, Li S (2020) Asymmetric co-teaching for unsupervised cross-domain person re-identification. In: Proceedings of the AAAI conference on artificial intelligence 34:12597–12604
[50]
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 770–778
[51]
Lin Y, Xie L, Wu Y, Yan C, Tian Q (2016) Unsupervised person re-identification via softened similarity learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition pp 3390–3399
[52]
Wang X, Doretto G, Sebastian T, Rittscher J, Tu P (2007) Shape and appearance context modeling. In: 2007 IEEE 11th international conference on computer vision. IEEE, pp 1–8
[53]
Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 10981–10990
[54]
Zhang H, Cao H, Yang X, Deng C, Tao D (2021) Self-training with progressive representation enhancement for unsupervised cross-domain person re-identification. IEEE Trans Image Process
[55]
Liu X, Zhang S (2020) Domain adaptive person re-identification via coupling optimization. In: Proceedings of the 28th ACM international conference on multimedia. pp 547–555
[56]
Xuan S, Zhang S(2021) Intra-inter camera similarity for unsupervised person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 11926–11935
[57]
Yang F, Zhong Z, Luo Z, Cai YZ, Lin Y, Li S, Sebe N (2021) Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 4855–4864
[58]
Ge Y, Zhu F, Chen D, Zhao R, et al. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id Adv Neural Inf Process Syst 2020 33 11309-11321
Recommendations
Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification
Computer Vision – ECCV 2020AbstractUnsupervised domain adaptation (UDA) in the task of person re-identification (re-ID) is highly challenging due to large domain divergence and no class overlap between domains. Pseudo-label based self-training is one of the representative ...
Multi-class center dynamic contrastive learning for unsupervised domain adaptation person re-identification
AbstractUnsupervised domain adaptation person re-identification (UDA Re-ID) aims to leverage the pedestrian knowledge learned from labeled source domain to assist in learning the pedestrian knowledge in the unlabeled target domain. Most of existing ...
Soft pseudo-Label shrinkage for unsupervised domain adaptive person re-identification
Highlights- We changed the title to “Soft Pseudo-Label Shrinkage for Unsupervised Domain Adaptive Person Re-identification”.
AbstractOne effective way to tackle unsupervised domain adaptation (UDA) on person re-identification (Re-ID) is to use clustering-based self-training approach, where a model is trained with hard pseudo-labels obtained from a clustering method. ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 October 2022
Accepted: 19 April 2022
Received: 22 October 2021
Author Tags
Qualifiers
- Research-article
Funding Sources
- Natural Science Foundation of China
- National Key R &D Program of China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Nov 2024
Other Metrics
Citations
View Options
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