Unsupervised Domain Adaptation in the Absence of Source Data
arXiv:2007.10233
Abstract
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.
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- On Calibration of Modern Neural Networks
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Generalizing to Unseen Domains via Adversarial Data Augmentation
- Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
- Test-Time Training with Self-Supervision for Generalization under Distribution Shifts