Abstract
Recently, supervised person re-identification (Re-ID) algorithms have achieved great performance on benchmarks. However, it highly depends on labeled training samples and may not generalize well to new domains, limiting the applicability of person Re-ID in practical. To this end, we propose a novel unsupervised domain adaptive approach to transfer the learned knowledge across diverse domains. To address the issue of lacking target domain annotations, we perform a supervised classification task using only labeled source data and share weights of two feature extraction networks. Considering unbalanced data distribution between the source domain and target domain, we then adopt a generative adversarial approach with GAN-based losses to reduce domain discrepancy and further improve Re-ID performance. The entire framework can be trained in an unsupervised manner with standard deep neural networks. Extensive experiments demonstrate that our proposed approach performs favourably against state-of-the-art methods.
Similar content being viewed by others
References
An L, Chen X, Liu S, Lei Y, Yang S (2017) Integrating appearance features and soft biometrics for person re-identification. Multim Tools Appl 76 (9):12117–12131
Chong Y, Peng C, Zhang J, Pan S (2019) Unsupervised cross-domain person re-identification based on style transfer. In: International conference on intelligent computing (ICIC), pp 54–64
Deng W, Zheng L, Jiao J (2018) Image-image domain adaptation with preserved self-Similarity and domain-dissimilarity for Person Re-identification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 994–1003
El N, He Y, Guan L (2019) Discriminative feature selection guided deep canonical correlation analysis. In: IEEE International conference on acoustics, speech and signal processing (ICASSP), pp 3487–3491
Fan H, Zheng L, Yang Y (2018) Unsupervised person re-identification: Clustering and fine-tuning. ACM Trans Mult Comput Commun Appl 14 (4):83:1–83:18
Genç A, Ekenel H (2019) Cross-dataset person re-identification using deep convolutional neural networks: effects of context and domain adaptation. Multimed Tools Appl 78(5):5843–5861
Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv:1703.07737
Imani M, Ghassemian H (2015) A manifold learning based feature extraction method with improved discriminative ability. In: Iranian conference on machine vision and image processing (MVIP), pp 29–32
Isola P, Zhu J, Zhou T, Efros A (2017) Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1125–1134
Li W, Rui Z, Tong X, Wang X (2014) Deep-reid: Deep filter pairing neural network for person re-identification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 152–159
Liao S, Hu Y, Zhu X, Li S (2015) Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2197–2206
Liao S, Li S (2015) Efficient psd constrained asymmetric metric learning for person re-identification. In: IEEE International conference on computer vision (ICCV), pp 3685–3693
Lin S, Li H, Li C, Kot A (2018) Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification. British Machine Vision Conference, pp 1–9
Liu J, Zha Z, Chen D, Hong R, Wang M (2019) Adaptive transfer network for cross-domain person re-identification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 7195–7204
Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. Int Conf Mach Learn 37:97–105
Luo Z, Zou Y, Hoffman J, Fei-Fei L (2017) Label efficient learning of transferable representations across domains and tasks. In: Conference on neural information processing systems (NIPS), pp 165–177
Lv J, Chen W, Li Q, Yang C (2018) Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 7948–7956
Ma W, Han H, Zhang Y, Wang C (2018) Metric learning algorithm based on weighted pairwise constrained component analysis for person re-identification. In: IEEE 18th International conference on communication technology (ICCT), pp 1154–1158
Murez Z, Kolouri S, Kriegman D, Ramamoorthi R, Kim K (2018) Image to image translation for domain adaptation. In: IEEE/CVF Conference on computer vision and pattern recognition (CVPR), pp 4500–4509
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: IEEE Conference on computer vision and pattern recognition (CVPR), pp 1306–1315
Rao W, Xu M, Zhou J (2020) Improved metric learning algorithm for person re-identification based on asymmetric metric. In: IEEE International conference on artificial intelligence and computer applications (ICAICA), pp 212–216
Ren C, Liang B, Ge P, Zhai Y, Lei Z (2020) Domain adaptive person re-identification via camera style generation and label propagation. IEEE Trans Inf Forensics Sec 15:1290–1302
Si J, Zhang H, Li C, Kuen J, Kong X, Kot A, Wang G (2018) Dual attention matching network for context-aware feature sequence based person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 5363–5372
Song L, Wang C, Zhang L, Du B, Zhang Q, Huang C, Wang X (2020) Unsupervised domain adaptive re-identification: Theory and practice. Pattern Recognit 102:107–173
Sun Y, Zheng L, Deng W, Wang S (2017) Svdnet for pedestrian retrieval. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 3820–3828
Tian Y, Li Q, Wang D, Wan B (2019) Robust joint learning network: improved deep representation learning for person re-identification. Multimed Tools Appl 78(17):24187–24203
Wang J, Zhu X, Gong S, Li W (2018) Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 2275–2284
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
Watson G, Bhalerao A (2020) Person re-identification combining deep features and attribute detection. Multimed Tools Appl 79(9-10):6463–6481
Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 79–88
Xie S, Zheng Z, Chen L, Chen C (2018) Learning semantic representations for unsupervised domain adaptation. In: Proceedings of the 35th international conference on machine learning (ICML), pp 5419–5428
Yang X, Zhou P, Wang M (2019) Person Reidentification via Structural Deep Metric Learning, vol 30, pp 2987–2998
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 (CVPR), pp 1239–1248
Zhang X, Wang S, Zhang L, Chun Z, Chang L (2016) Ensemble feature selection with discriminative and representative properties for malware detection. In: IEEE Conference on computer communications workshops, pp 674–675
Zheng W, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 649–656
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 (ICCV), pp 1116–1124
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 (ICCV), pp 3754–3762
Zhong Z, Zheng L, Zheng Z, Li S, Yang Y (2018) Camera Style Adaptation for Person Re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 5157–5166
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 (CVPR), pp 2921–2929
Zhu J, Park T, Isola P, Efros A (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp 2223–2232
Acknowledgements
This work was supported by the Nature Science Foundation of China (No.61762023), the Sprouts Come Special Project of GuiZhou Department of Science and Technology (No. QKHPTRC [2017]5726) and the Startup Project of Doctoral Research of Guizhou Normal University (2017).
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
Liu, H., Guo, F. & Xia, D. Domain adaptation with structural knowledge transfer learning for person re-identification. Multimed Tools Appl 80, 29321–29337 (2021). https://doi.org/10.1007/s11042-021-11139-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11139-w