Source-Free Active Domain Adaptation via Augmentation-Based Sample Query and Progressive Model Adaptation

Active domain adaptation (ADA), which enormously improves the performance of unsupervised domain adaptation (UDA) at the expense of annotating limited target data, has attracted a surge of interest. However, in real-world applications, the source data in conventional ADA are not always accessible due to data privacy and security issues. To alleviate this dilemma, we introduce a more practical and challenging setting, dubbed as source-free ADA (SFADA), where one can select a small quota of target samples for label query to assist the model learning, but labeled source data are unavailable. Therefore, how to query the most informative target samples and mitigate the domain gap without the aid of source data are two key challenges in SFADA. To address SFADA, we propose a unified method <italic>SQAdapt</italic> via augmentation-based <italic>S</italic>ample <italic>Q</italic>uery and progressive model <italic>Adapt</italic>ation. In specific, an active selection module (ASM) is built for target label query, which exploits data augmentation to select the most informative target samples with high predictive sensitivity and uncertainty. Then, we further introduce a classifier adaptation module (CAM) to leverage both the labeled and unlabeled target data for progressively calibrating the classifier weights. Meanwhile, the source-like target samples with low selection scores are taken as source surrogates to realize the distribution alignment in the source-free scenario by the proposed distribution alignment module (DAM). Moreover, as a general active label query method, <italic>SQAdapt</italic> can be easily integrated into other source-free UDA (SFUDA) methods, and improve their performance. Comprehensive experiments on multiple benchmarks have shown that <italic>SQAdapt</italic> can achieve superior performance and even surpass most of the ADA methods.