Affiliation:
1. College of Information Science and Engineering, Northeastern University, Shenyang, China
Abstract
Clustering-based unsupervised domain adaptive person re-identification methods have achieved remarkable progress. However, existing works are easy to fall into local minimum traps due to the optimization of two variables, feature representation and pseudo labels. Besides, the model can also be hurt by the inevitable false assignment of pseudo labels. In order to solve these problems, we propose the Doubly Stochastic Subdomain Mining (DSSM) to prevent the nonconvex optimization from falling into local minima in this paper. And we also design a novel reweighting algorithm based on the similarity correlation coefficient between samples which is referred to as Maximal Heterogeneous Similarity (MHS), it can reduce the adverse effect caused by noisy labels. Extensive experiments on two popular person re-identification datasets demonstrate that our method outperforms other state-of-the-art works. The source code is available at https://github.com/Tchunansheng/DSSM.
Reference38 articles.
1. A density-based spatial clustering of application with noise;Bäcklund;Data Mining TNM033,2011
2. Z. Bai, Z. Wang, J. Wang, D. Hu and E. Ding, Unsupervised multi-source domain adaptation for person re-identification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12914–12923.
3. A. Brutzkus and A. Globerson, Globally optimal gradient descent for a convnet with Gaussian inputs, in: International Conference on Machine Learning, PMLR, 2017, pp. 605–614.
4. G. Chen, Y. Lu, J. Lu and J. Zhou, Deep credible metric learning for unsupervised domain adaptation person re-identification, in: Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII, Vol. 16, Springer, 2020, pp. 643–659.
5. Y. Chen, X. Zhu and S. Gong, Instance-guided context rendering for cross-domain person re-identification, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 232–242.