Revisiting Source-Free Domain Adaptation: a New Perspective via Uncertainty Control

Source-Free Domain Adaptation (SFDA) seeks to adapt a pre-trained source model to a target domain using only unlabeled target data, without access to the original source data. While current state-of-the-art methods rely on leveraging weak supervision from the source model to extract reliable information for self-supervised adaptation, they often overlook the uncertainty that arises during the transfer process. In this paper, we conduct a systematic and theoretical analysis of the uncertainty inherent in existing SFDA methods and demonstrate its impact on transfer performance through the lens of Distributionally Robust Optimization. Building upon the theoretical results, we propose a novel instance-dependent uncertainty control algorithm for SFDA. Our method quantifies and exploits the uncertainty during adaptation, significantly improving model performance. Extensive experiments on benchmark datasets and empirical analyses confirm our theoretical findings and the effectiveness of the proposed method. This work offers new insights into understanding and advancing SFDA performance. We release our code at https://github.com/xugezheng/UCon_SFDA .