Abstract
State-of-the-art Re-ID methods based on unsupervised domain adaption transferred the domain knowledge by pre-training model on labeled source domain and fine-tuned the pre-trained model with pseudo labels generated by clustering samples on unlabeled target domain. Unfortunately, compared with supervised Re-ID methods, the performance of exiting clustering-based UDA Re-ID methods dropped sharply, since these methods utilized a not good enough baseline and seldom handled the noisy pseudo labels generated by clustering algorithm. In this paper, we try to address the UDA problem by designing a Strong Clustering-based Unsupervised Re-ID (SCURID) baseline for further research at first. Then, we integrate the hard labels and soft multilabels to learn more discriminative features on a unified angular regularized metric space. Specifically, we design the angular margin losses consisting of Hard Angular Margin Identification (HAMI) loss and Soft Angular Margin Identification (SAMI) loss. The HAMI loss can learn generalizable and discriminative features through hard pseudo labels generated by clustering on unlabeled target domain. The SAMI loss is proposed to refine the hard noisy pseudo labels through the soft multilabels obtained from peer network. Benefited from SCURID baseline and two angular margin losses, it enables the clustering-based UDA Re-ID model to alleviate the negative effect of noisy labels and toward more discriminability. Comprehensive and extensive experiments on three public available Re-ID datasets, e.g., Matket-1501, DukeMTMC-reID and MSMT17, demonstrate that our proposed method can outperform the state-of-the-art results on UDA Re-ID task.
Similar content being viewed by others
References
Motiian S, Piccirilli M, Adjeroh DA, Doretto G (2017) Unified deep supervised domain adaptation and generalization. In: ICCV, pp. 5715–5725
Chen Y, Li W, Sakaridis C, Dai D, Van Gool L (2018) Domain adaptive faster r-cnn for object detection in the wild. In: CVPR, pp. 3339–3348
Chen Y, Li W, Van Gool L (2018) Road: reality oriented adaptation for semantic segmentation of urban scenes. In: CVPR, pp. 7892–7901
Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification: clustering and fine-tuning. TOMM 14(4):1–18
Zhang X, Cao J, Shen C, You M (2019) Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: ICCV, pp. 8222–8231
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: ICCV, pp. 6112–6121
Wu J, Liao S, Wang X, Yang Y, Li SZ et al. (2019) Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification. In: 2019 IEEE International conference on multimedia and expo (ICME).IEEE, pp. 886–891
Yang F, 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, vol. 34, no. 07, pp. 12 597–12 604
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: CVPR, pp. 9021–9030
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp. 770–778
Pan X, Luo P, Shi J, Tang X (2018) Two at once: enhancing learning and generalization capacities via ibn-net. In: ECCV, pp. 464–479
Arthur D, Vassilvitskii S (2006) k-means++: The advantages of careful seeding. Tech. Rep, Stanford
Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2016) Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530
Deng J, Guo J, Xue N, Zafeiriou S (2019) Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4690–4699
Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. In: ICML, vol. 2, no. 3, p. 7
Ranjan R, Bansal A, Xu H, Sankaranarayanan S, Chen J-C, Castillo CD, Chellappa R (2018) Crystal loss and quality pooling for unconstrained face verification and recognition. arXiv preprint arXiv:1804.01159
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 212–220
Fan X, Jiang W, Luo H, Fei M (2019) Spherereid: deep hypersphere manifold embedding for person re-identification. J Vis Commun Image Represent 60:51–58
Hao Y, Wang N, Li J, Gao X (2019) Hsme: hypersphere manifold embedding for visible thermal person re-identification. Proc AAAI Conf Artif Intell 33(01):8385–8392
Zhu Z, Jiang X, Zheng F, Guo X, Huang F, Sun X, Zheng W (2020) Aware loss with angular regularization for person re-identification. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, pp. 13 114–13 121
Sovrasov V, Sidnev D (2020) Building computationally efficient and well-generalizing person re-identification models with metric learning. arXiv preprint arXiv:2003.07618
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
Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: CVPR, pp. 1318–1327
Zhang X, Luo H, Fan X, Xiang W, Sun Y, Xiao Q, Jiang W, Zhang C, Sun J (2017) Alignedreid: surpassing human-level performance in person re-identification. arXiv preprint arXiv:1711.08184
Bai X, Yang M, Huang T, Dou Z, Yu R, Xu Y (2020) Deep-person: learning discriminative deep features for person re-identification. Pattern Recognit 98:107036
Zheng L, Huang Y, Lu H, Yang Y (2019) Pose-invariant embedding for deep person re-identification. IEEE Trans Image Process 28(9):4500–4509
Sarfraz MS, Schumann A, Eberle A, Stiefelhagen R (2018) A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In: CVPR, pp. 420–429
Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV, pp. 480–496
Wang G, Yuan Y, Chen X, Li J, Zhou X (2018) Learning discriminative features with multiple granularities for person re-identification. In: ACM MM, pp. 274–282
Zhang W, Huang L, Wei Z, Nie J (2021) Appearance feature enhancement for person re-identification. Expert Syst Appl 163:113771
Li S, Liu X, Liu W, Ma H, Zhang H (2016) “A discriminative null space based deep learning approach for person re-identification. In: 2016 4th International conference on cloud computing and intelligence systems (CCIS). IEEE, pp. 480–484
He L, Wang Y, Liu W, Zhao H, Sun Z, Feng J (2019) Foreground-aware pyramid reconstruction for alignment-free occluded person re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision, ,pp. 8450–8459
Xie H, Fang S, Zha Z-J, Yang Y, Li Y, Zhang Y (2019) Convolutional attention networks for scene text recognition. ACM Trans Multimed, Comput, Commun Appl (TOMM) 15(1s):1–17
Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: ECCV. Springer, pp. 262–275
Liao S, Hu Y, Zhu X, Li SZ (2015) Person re-identification by local maximal occurrence representation and metric learning. In: CVPR, pp. 2197–2206
Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp. 2360–2367
Matsukawa T, Okabe T, Suzuki E, Sato Y (2016) Hierarchical gaussian descriptor for person re-identification. In: CVPR, pp. 1363–1372
Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124
Peng P, Xiang T, Wang Y, Pontil M, Gong S, Huang T, Tian Y (2016) Unsupervised cross-dataset transfer learning for person re-identification. In: CVPR, pp. 1306–1315
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: CVPR, pp. 994–1003
Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: CVPR, pp. 79–88
Wang J, Zhu X, Gong S, Li W (2018) Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: CVPR, pp. 2275–2284
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
Liu J, Zha Z-J, Chen D, Hong R, Wang M (2019) Adaptive transfer network for cross-domain person re-identification. In: CVPR, pp. 7202–7211
Huang Y, Wu Q, Xu J, Zhong Y (2019) Sbsgan: suppression of inter-domain background shift for person re-identification. In: ICCV, pp. 9527–9536
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: ICCV, pp. 8080–8089
Li Y-J, Lin C-S, Lin Y-B, Wang Y-CF (2019) Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In: ICCV, pp. 7919–7929
Chen Y, Zhu X, Gong S (2019) Instance-guided context rendering for cross-domain person re-identification. In: ICCV, pp. 232–242
Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. In: CVPR, pp. 598–607
Yu H-X, Zheng W-S, Wu A, Guo X, Gong S, Lai J-H (2019) Unsupervised person re-identification by soft multilabel learning. In: CVPR, pp. 2148–2157
Zhang W, Wei Z, Huang L, Xie K, Qin Q (2020) Adaptive attention-aware network for unsupervised person re-identification. Neurocomputing 411:20–31
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. AAAI 33(01):8738–8745
Zheng L, Zhang H, Sun S, Chandraker M, Yang Y, Tian Q (2017) Person re-identification in the wild. In: CVPR, pp. 1367–1376
Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: CVPR, pp. 1249–1258
Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. In: CVPR, pp. 3908–3916
Zheng Z, Zheng L, Yang Y (2017) A discriminatively learned cnn embedding for person reidentification. TOMM 14(1):1–20
Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737
Yuan Y, Chen W, Yang Y, Wang Z (2020) In defense of the triplet loss again: Learning robust person re-identification with fast approximated triplet loss and label distillation. In: CVPRW, pp. 354–355
Salimans T, Kingma DP (2016) Weight normalization: a simple reparameterization to accelerate training of deep neural networks. arXiv preprint arXiv:1602.07868
Tarvainen A, Valpola H (2017) Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780
Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV, pp. 17–35
Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. TPAMI 32(9):1627–1645
Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: towards real-time object detection with region proposal networks. TPAMI 39(6):1137–1149
Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: AAAI, vol. 34, no. 07, pp. 13 001–13 008
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: CVPR. IEEE pp. 248–255
Yang Q, Yu H-X, Wu A, Zheng W-S (2019) Patch-based discriminative feature learning for unsupervised person re-identification. In: CVPR, pp. 3633–3642
Wu A, Zheng W-S, Lai J-H (2019) Unsupervised person re-identification by camera-aware similarity consistency learning. In: ICCV, pp. 6922–6931
Huang Y, Peng P, Jin Y, Li Y, Xing J (2020) Domain adaptive attention learning for unsupervised person re-identification. In: AAAI, vol. 34, no. 07, pp. 11 069–11 076
Mekhazni D, Bhuiyan A, Ekladious G, Granger E (2020) Unsupervised domain adaptation in the dissimilarity space for person re-identification. In: ECCV, pp. 159–174
Zou Y, Yang X, Yu Z, Kumar B, Kautz J (2020) Joint disentangling and adaptation for cross-domain person re-identification. arXiv preprint arXiv:2007.10315
Ester M, Kriegel H-P, Sander J, Xu X et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. Kdd 96(34):226–231
Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):2579–2605
Acknowledgements
This work is supported by the National Natural Science Foundation of China (No. 61872326, No.61672475); Shandong Provincial Natural Science Foundation (ZR2019MF044).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, W., Huang, L., Wei, Z. et al. Angular regularization for unsupervised domain adaption on person re-identification. Neural Comput & Applic 33, 17041–17056 (2021). https://doi.org/10.1007/s00521-021-06297-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06297-9