Abstract
Unsupervised domain adaptation in person re-identification is a challenging task. The performance of models trained on a specific domain generally degrades significantly on other domains due to the domain gaps. State-of-the-art clustering-based cross-domain methods inevitably introduce noisy labels. The negative effects of noisy labels gradually accumulate during iterative training. Besides, optimizing with conventional triplet loss could make the model stuck in local optima in the late stage of domain adaptation. To mitigate the effects of noisy labels, this paper proposes an asymmetric mutual learning framework which cooperates two models with asymmetric labels. The learned asymmetric information is helpful for the two models to complement with each other. Specifically, we propose a merging clusters algorithm to generate asymmetric labels. We also introduce a similarity weighted loss which can further adapt the model to target domain. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods on three popular person re-identification datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: 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 (2018)
Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Knowledge Discovery and Data Mining, pp. 226–231 (1996)
Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: 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 (2019)
Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: International Conference on Learning Representations (2020)
Han, B., et al.: Co-teaching: Robust training of deep neural networks with extremely noisy labels. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 8536–8546 (2018)
Huang, H., et al.: Eanet: enhancing alignment for cross-domain person re-identification. arXiv preprint arXiv:1812.11369 (2018)
Li, P., Xu, Y., Wei, Y., Yang, Y.: Self-correction for human parsing. arXiv preprint arXiv:1910.09777 (2019)
Liu, J., Zha, Z.J., Chen, D., Hong, R., Wang, M.: Adaptive transfer network for cross-domain person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7202–7211 (2019)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1487–1495 (2019)
Song, J., Yang, Y., Song, Y.Z., Xiang, T., Hospedales, T.M.: Generalizable person re-identification by domain-invariant mapping network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 2019
Song, L., et al.: Unsupervised domain adaptive re-identification: Theory and practice. Pattern Recognition 102, 107173 (2020)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision, pp. 480–496 (2018)
Wei, L., Zhang, S., Gao, W., Tian, Q.: 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 (2018)
Yang, F., et al.: Asymmetric co-teaching for unsupervised cross-domain person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12597–12604 (2020)
Zhai, Y., et al.: Ad-cluster: augmented discriminative clustering for domain adaptive person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9021–9030 (2020)
Zhang, X., Cao, J., Shen, C., You, M.: 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 (2019)
Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320–4328 (2018)
Zhao, F., Liao, S., Xie, G.-S., Zhao, J., Zhang, K., Shao, L.: Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 526–544. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_31
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)
Zheng, Z., Zheng, L., Yang, Y.: 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 (2017)
Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1318–1327 (2017)
Zhong, Z., Zheng, L., Luo, Z., Li, S., Yang, Y.: 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 (2019)
Acknowledgment
This work is supported by National Key R&D Program of China (Grant No. 2018YF B2100603) and National Natural Science Foundation of China (Grant No. 61872024).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, D., Zhang, L., Diao, Q., Wu, W., Zhou, Z. (2021). Asymmetric Mutual Learning for Unsupervised Cross-Domain Person Re-identification. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13033. Springer, Cham. https://doi.org/10.1007/978-3-030-89370-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-89370-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89369-9
Online ISBN: 978-3-030-89370-5
eBook Packages: Computer ScienceComputer Science (R0)