Unsupervised Domain Adaptation in the Absence of Source Data
This addresses domain adaptation for users with pre-trained models but no source data, though it is incremental as it builds on existing adaptation methods.
The paper tackles the problem of adapting a pre-trained classifier to a target domain without access to source data, focusing on natural shifts like brightness and contrast, and shows that it outperforms fine-tuning baselines in limited labeled data scenarios.
Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is reasonable to assume that source data is unavailable. We propose an unsupervised method for adapting a source classifier to a target domain that varies from the source domain along natural axes, such as brightness and contrast. Our method only requires access to unlabeled target instances and the source classifier. We validate our method in scenarios where the distribution shift involves brightness, contrast, and rotation and show that it outperforms fine-tuning baselines in scenarios with limited labeled data.