De-Confusing Pseudo-Labels in Source-Free Domain Adaptation
This addresses the challenge of adapting models to new domains without source data, which is incremental as it builds on existing self-training methods like SHOT.
The paper tackles the problem of noisy pseudo-labels in source-free domain adaptation by introducing a noise-learning approach that estimates a noise transition matrix to capture label corruption and improve true class-posterior estimation, achieving state-of-the-art results on datasets like VisDA, DomainNet, and OfficeHome.
Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that usually includes pseudo-labeling techniques. In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings and learn to de-confuse the pseudo-labels. More specifically, we learn a noise transition matrix of the pseudo-labels to capture the label corruption of each class and learn the underlying true label distribution. Estimating the noise transition matrix enables a better true class-posterior estimation, resulting in better prediction accuracy. We demonstrate the effectiveness of our approach when combined with several source-free domain adaptation methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.