Exploring Domain-Invariant Parameters for Source Free Domain Adaptation

Fan Wang, Zhongyi Han, Yongshun Gong, Yilong Yin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 7151-7160


Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of a well-trained source model to an unlabeled target domain, which is critical in various privacy-preserving scenarios. Most existing methods focus on learning the domain-invariant representations depending solely on the target data, leading to the obtained representations are target-specific. In this way, they cannot fully address the distribution shift problem across domains. In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model. The motivation behind this insight is clear: the domain-invariant representations are dominated by only partial parameters of an available deep source model. We devise the Domain-Invariant Parameter Exploring (DIPE) approach to capture such domain-invariant parameters in the source model to generate domain-invariant representations. A distinguishing method is developed correspondingly for two types of parameters, i.e., domain-invariant and domain-specific parameters, as well as an effective update strategy based on the clustering correction technique and a target hypothesis is proposed. Extensive experiments verify that DIPE successfully exceeds the current state-of-the-art models on many domain adaptation datasets.

Related Material

@InProceedings{Wang_2022_CVPR, author = {Wang, Fan and Han, Zhongyi and Gong, Yongshun and Yin, Yilong}, title = {Exploring Domain-Invariant Parameters for Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {7151-7160} }