Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation

Abstract

Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc. Most domain adaptation methods learn domain-invariant features with data from both domains available. However, such a strategy might be infeasible in practice when source data are unavailable due to data-privacy concerns. To address this issue, we propose a novel adaptation method via hypothesis transfer without accessing source data at adaptation stage. In order to fully use the limited target data, a semi-supervised mutual enhancement method is proposed, in which entropy minimization and augmented label propagation are used iteratively to perform inter-domain and intra-domain alignments. Compared with state-of-the-art methods, the experimental results on three public datasets demonstrate that our method gets up to 19.9% improvements on semi-supervised adaptation tasks.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Rényi Divergence and Kullback-Leibler Divergence
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Conditional Adversarial Domain Adaptation
• Weight Uncertainty in Neural Networks
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• Tent: Fully Test-time Adaptation by Entropy Minimization
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning