Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification

TL;DR

This paper introduces an uncertainty-aware clustering framework for unsupervised domain adaptive object re-identification, improving clustering quality and label reliability to enhance model performance across domains.

Contribution

It proposes a hierarchical clustering scheme and an uncertainty-aware instance selection method, advancing the state-of-the-art in unsupervised domain adaptive object Re-ID.

Findings

Achieves state-of-the-art results on multiple UDA Re-ID tasks.

Reduces the performance gap between unsupervised and supervised Re-ID.

Outperforms fully supervised methods in certain transfer tasks.

Abstract

Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain. State-of-the-art object Re-ID approaches adopt clustering algorithms to generate pseudo-labels for the unlabeled target domain. However, the inevitable label noise caused by the clustering procedure significantly degrades the discriminative power of Re-ID model. To address this problem, we propose an uncertainty-aware clustering framework (UCF) for UDA tasks. First, a novel hierarchical clustering scheme is proposed to promote clustering quality. Second, an uncertainty-aware collaborative instance selection method is introduced to select images with reliable labels for model training. Combining both techniques effectively reduces the impact of noisy labels. In addition, we introduce a strong baseline that features a compact contrastive loss. Our UCF method consistently achieves state-of-the-art performance in multiple UDA tasks for object Re-ID, and significantly reduces the gap between unsupervised and supervised Re-ID performance. In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501. The code of UCF is available at https://github.com/Wang-pengfei/UCF.