Domain Adaptation without Source Data

TL;DR

This paper introduces a source data-free domain adaptation method that leverages a pre-trained source model and self-learning to adapt to new target domains without accessing sensitive source data, outperforming traditional methods.

Contribution

The paper proposes a novel source data-free domain adaptation approach using self-entropy, class prototypes, and set-to-set filtering to effectively adapt models without source data.

Findings

Outperforms conventional domain adaptation methods on benchmark datasets.

Effectively uses self-entropy and class prototypes for pseudo-labeling.

Reduces uncertainty with set-to-set filtering without hyperparameters.

Abstract

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real-world and possibly causes data-privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. To avoid accessing source data that may contain sensitive information, we introduce Source data-Free Domain Adaptation (SFDA). Our key idea is to leverage a pre-trained model from the source domain and progressively update the target model in a self-learning manner. We observe that target samples with lower self-entropy measured by the pre-trained source model are more likely to be classified correctly. From this, we select the reliable samples with the self-entropy criterion and define these as class prototypes. We then assign pseudo labels for every target sample based on the similarity score with class prototypes. Furthermore, to reduce the uncertainty from the pseudo labeling process, we propose set-to-set distance-based filtering which does not require any tunable hyperparameters. Finally, we train the target model with the filtered pseudo labels with regularization from the pre-trained source model. Surprisingly, without direct usage of labeled source samples, our PrDA outperforms conventional domain adaptation methods on benchmark datasets. Our code is publicly available at https://github.com/youngryan1993/SFDA-SourceFreeDA