CoSDA: Continual Source-Free Domain Adaptation
This addresses the problem of data privacy and forgetting in domain adaptation for machine learning practitioners, but it is incremental as it builds on existing SFDA methods.
The paper tackles catastrophic forgetting in source-free domain adaptation (SFDA) by proposing CoSDA, a method using a teacher-student model with consistency regularization, which outperforms state-of-the-art approaches in continuous adaptation benchmarks.
Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data. To systematically investigate the mechanism of catastrophic forgetting, we first reimplement previous SFDA approaches within a unified framework and evaluate them on four benchmarks. We observe that there is a trade-off between adaptation gain and forgetting loss, which motivates us to design a consistency regularization to mitigate forgetting. In particular, we propose a continual source-free domain adaptation approach named CoSDA, which employs a dual-speed optimized teacher-student model pair and is equipped with consistency learning capability. Our experiments demonstrate that CoSDA outperforms state-of-the-art approaches in continuous adaptation. Notably, our CoSDA can also be integrated with other SFDA methods to alleviate forgetting.