Casting a BAIT for Offline and Online Source-free Domain Adaptation
This addresses domain adaptation for scenarios where only a pre-trained source model is available, with incremental improvements in online settings.
The paper tackles source-free domain adaptation (SFDA) by introducing a second classifier to identify misclassified features and push them towards the correct side of the source decision boundary, achieving competitive results in offline SFDA and surpassing other methods by a large margin in online SFDA.
We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be visited multiple times (epochs) to arrive at a prediction for each target sample, and the online setting where the target data needs to be directly classified upon arrival. Inspired by diverse classifier based domain adaptation methods, in this paper we introduce a second classifier, but with another classifier head fixed. When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features. Next, when updating the feature extractor, those features will be pushed towards the right side of the source decision boundary, thus achieving source-free domain adaptation. Experimental results show that the proposed method achieves competitive results for offline SFDA on several benchmark datasets compared with existing DA and SFDA methods, and our method surpasses by a large margin other SFDA methods under online source-free domain adaptation setting.