A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
This addresses the challenge of adapting models to new domains without source data, which is important for privacy and cost concerns in real-world applications, but it is incremental as it builds on existing SFUDA methods.
The paper tackles the problem of source-free unsupervised domain adaptation (SFUDA) by proposing Experts Cooperative Learning (EXCL), which combines a frozen source model and a vision-language model to mine consensus knowledge from unlabeled target data, achieving state-of-the-art performance on four benchmark datasets.
Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data, driven by concerns over privacy and cost. Existing SFUDA methods either exploit only the source model's predictions or fine-tune large multimodal models, yet both neglect complementary insights and the latent structure of target data. In this paper, we propose the Experts Cooperative Learning (EXCL). EXCL contains the Dual Experts framework and Retrieval-Augmentation-Interaction optimization pipeline. The Dual Experts framework places a frozen source-domain model (augmented with Conv-Adapter) and a pretrained vision-language model (with a trainable text prompt) on equal footing to mine consensus knowledge from unlabeled target samples. To effectively train these plug-in modules under purely unsupervised conditions, we introduce Retrieval-Augmented-Interaction(RAIN), a three-stage pipeline that (1) collaboratively retrieves pseudo-source and complex target samples, (2) separately fine-tunes each expert on its respective sample set, and (3) enforces learning object consistency via a shared learning result. Extensive experiments on four benchmark datasets demonstrate that our approach matches state-of-the-art performance.