Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification
This work addresses domain adaptation challenges in person re-identification, an incremental improvement over existing clustering-based methods.
The paper tackles noisy pseudo labels and unreliable generalization in unsupervised domain adaptive person re-identification by proposing Feature Diversity Learning with Sample Dropout, achieving state-of-the-art performance on multiple benchmark datasets.
Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.