Jacobian Norm for Unsupervised Source-Free Domain Adaptation
This work addresses a practical problem for machine learning practitioners by enhancing adaptation performance in data-scarce scenarios, though it is incremental as it builds on existing USFDA methods.
The paper tackles the challenge of unsupervised source-free domain adaptation (USFDA) where source data is unavailable, by proposing a Jacobian norm regularizer based on model smoothness to improve target generalization, achieving superior results on benchmark datasets with minimal code changes.
Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain. In such a scenario, all conventional adaptation methods that require source data fail. To combat this challenge, existing USFDAs turn to transfer knowledge by aligning the target feature to the latent distribution hidden in the source model. However, such information is naturally limited. Thus, the alignment in such a scenario is not only difficult but also insufficient, which degrades the target generalization performance. To relieve this dilemma in current USFDAs, we are motivated to explore a new perspective to boost their performance. For this purpose and gaining necessary insight, we look back upon the origin of the domain adaptation and first theoretically derive a new-brand target generalization error bound based on the model smoothness. Then, following the theoretical insight, a general and model-smoothness-guided Jacobian norm (JN) regularizer is designed and imposed on the target domain to mitigate this dilemma. Extensive experiments are conducted to validate its effectiveness. In its implementation, just with a few lines of codes added to the existing USFDAs, we achieve superior results on various benchmark datasets.