Abstract
Cross-domain person re-identification (re-ID) has attracted much attention due to its wide applications in the field of computer vision and surveillance. However, the domain shift issue leads to unsatisfactory generalization performance of a model on an unseen target domain when the model is trained on the source domain. Current methods usually adopt clustering methods to assign pseudo labels for unlabeled target images, resulting in high dependence on the performance of clustering method. In this paper, we firstly focus on extracting universal domain-adaptive features by designing a domain-adaptive-attention-based-dropout (DAAD) layer. DAAD layer is achieved by a universal attention-based dropout adapter (ADA) bank to hide the most discriminative region stochastically and a domain attention module to assign weights to the two domains (source and target). Then two feature memories are introduced according to one-shot learning in which only one image is annotated for each target identity. These two memories are designed to store target features from labeled and unlabeled images, respectively. The labeled feature memory is leveraged to estimate pseudo labels for these unlabeled images while the unlabeled feature memory aims to maximize distances between all the unlabeled images and minimize distances between similar images simultaneously. Extensive experiments on three re-ID datasets (DukeMTMC-reID, Market-1501, and MSMT17) demonstrate that the proposed model is effective to improve the domain adaptation performance than existing techniques.
Similar content being viewed by others
References
Bak S, Carr P (2017) One-shot metric learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2990–2999
Bousmalis K, Silberman N, Dohan D, Erhan D, Krishnan D(2017) Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3722–3731
Chen KW, Lai CC, Lee PJ, Chen CS, Hung YP (2011) Adaptive learning for target tracking and true linking discovering across multiple non-overlapping cameras. IEEE Trans Multimed 13(4):625–638
Chen T, Ding S, Xie J, Yuan Y, Chen W, Yang Y, Ren Z, Wang Z (2019) Abd-net: Attentive but diverse person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 8351–8361
Choe J, Shim H (2019) Attention-based dropout layer for weakly supervised object localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2219–2228
Chong Y, Peng C, Zhang J, Pan S (2021) Style transfer for unsupervised domain-adaptive person re-identification. Neurocomputing (NC) 422:314–321
Deng J, Dong W, Socher R, Li L.J, Li K, Fei-Fei L(2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 248–255
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
Ding Y, Fan H, Xu M, Yang Y (2020) Adaptive exploration for unsupervised person re-identification. ACM Trans Multimed Comput Commun Appl 16(1):1551–6857
Dong H, Lu P, Zhong S, Liu C, Ji Y, Gong S (2018) Person re-identification by enhanced local maximal occurrence representation and generalized similarity metric learning. Neurocomputing 307:25–37
Dong X, Yu S.I, Weng X, Wei S.E, Yang Y, Sheikh Y (2018) Supervision-by-registration: an unsupervised approach to improve the precision of facial landmark detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 360–368
Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification: clustering and fine-tuning. ACM Trans Multimed Comput Commun Appl (TOMM) 14(4):1–18
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
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning (ICML), pp 325–333
Gretton A, Borgwardt K, Rasch M, Schölkopf B, Smola A.J (2007) A kernel method for the two-sample-problem. In: Advances in neural information processing systems, pp 513–520
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
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Ji Z, Wang H, Han J, Pang Y (2020) SMAN: stacked multimodal attention network for cross-modal image-text retrieval. IEEE Trans Cybern (TCYB). https://doi.org/10.1109/TCYB.2020.2985716
Ji Z, Xiong K, Pang Y, Li X (2019) Video summarization with attention-based encoder-decoder networks. IEEE Trans Circuits Syst Video Technol (TCSVT) 30(6):1709–1717
Li W, Zhu X, Gong S (2018) Harmonious attention network for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285–2294
Li Z, Tang J (2015) Unsupervised feature selection via nonnegative spectral analysis and redundancy control. IEEE Trans Image Process 24(12):5343–5355
Lin S, Li H, Li C.T, Kot A.C (2018) Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. arXiv preprint arXiv:1807.01440
Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. In: Proceedings of the AAAI conference on artificial intelligence vol 33, pp 8738–8745
Lin Y, Guo F, Cao L, Wang J (2016) Person re-identification based on multi-instance multi-label learning. Neurocomputing 217:19–26
Liu H, Xiao Z, Fan B, Zeng H, Zhang Y, Jiang G (2021) PrGCN: probability prediction with graph convolutional network for person re-identification. Neurocomputing (NC) 423:57–70
Rezaei S, Tahmoresnezhad J, Solouk V (2020) A transductive transfer learning approach for image classification. Int J Mach Learn Cybern 12(3):747–762
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, New York, pp 17–35
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Song L, Cheng W, Zhang L, Bo D, Wang X (2018) Unsupervised domain adaptive re-identification: theory and practice. ArxivPrint, arXiv:1807.11334
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
Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In: IEEE computer society conference on computer vision and pattern recognition (CVPR), pp 10981–10990
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
Wang X, Bao A, Cheng Y, Yu Q (2019) Weight-sharing multi-stage multi-scale ensemble convolutional neural network. Int J Mach Learn Cybern 10(7):1631–1642
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
Wu Y, Lin Y, Dong X, Yan Y, Bian W, Yang Y (2019) Progressive learning for person re-identification with one example. IEEE Trans Image Process 28(6):2872–2881
Xia B.N, Gong Y, Zhang Y, Poellabauer C (2019) Second-order non-local attention networks for person re-identification. In: Proceedings of the IEEE international conference on computer vision, pp 3760–3769
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: the AAAI conference on artificial intelligence (AAAI), pp 12597–12604
Yu C, Wang J, Chen Y, Qin X (2019) Transfer channel pruning for compressing deep domain adaptation models. Int J Mach Learn Cybern 10(11):3129–3144
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
Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848–6856
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
Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. ArxivPrint, arXiv:1610.02984
Zheng M, Karanam S, Wu Z, Radke RJ (2019) Re-identification with consistent attentive siamese networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5735–5744
Zheng W, Gong S, Xiang T (2016) Towards open-world person re-identification by one-shot group-based verification. IEEE Trans Pattern Anal Mach Intell (TPAMI) 38(3):591–606. https://doi.org/10.1109/TPAMI.2015.2453984
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
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
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
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
Zhong Z, Zheng L, Zhenga Z, Li S, Yang Y (2019) Camstyle: a novel data augmentation method for person re-identification. IEEE Trans Image Process (TIP) 28(3):1176–1190
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921–2929
Acknowledgements
This work is partially supported by National Natural Science Foundation of China under Grant nos. 61872188, U1713208, 61972204, 61672287, 61861136011, 61773215.
Author information
Authors and Affiliations
Corresponding author
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
Song, X., Jin, Z. Domain adaptive attention-based dropout for one-shot person re-identification. Int. J. Mach. Learn. & Cyber. 13, 255–268 (2022). https://doi.org/10.1007/s13042-021-01399-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01399-1