Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification
This addresses the challenge of reducing annotation costs in person re-identification across domains, but it is incremental as it builds on existing clustering-based methods.
The paper tackles the problem of noisy pseudo labels in unsupervised domain adaptive person re-identification by proposing a probabilistic uncertainty-guided progressive label refinery method, achieving state-of-the-art performance with improvements such as 6.5% mAP over the baseline on Duke2Market and 2.5% mAP over prior methods on Market2MSMT.
Clustering-based unsupervised domain adaptive (UDA) person re-identification (ReID) reduces exhaustive annotations. However, owing to unsatisfactory feature embedding and imperfect clustering, pseudo labels for target domain data inherently contain an unknown proportion of wrong ones, which would mislead feature learning. In this paper, we propose an approach named probabilistic uncertainty guided progressive label refinery (P$^2$LR) for domain adaptive person re-identification. First, we propose to model the labeling uncertainty with the probabilistic distance along with ideal single-peak distributions. A quantitative criterion is established to measure the uncertainty of pseudo labels and facilitate the network training. Second, we explore a progressive strategy for refining pseudo labels. With the uncertainty-guided alternative optimization, we balance between the exploration of target domain data and the negative effects of noisy labeling. On top of a strong baseline, we obtain significant improvements and achieve the state-of-the-art performance on four UDA ReID benchmarks. Specifically, our method outperforms the baseline by 6.5% mAP on the Duke2Market task, while surpassing the state-of-the-art method by 2.5% mAP on the Market2MSMT task.