Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

TL;DR

This paper introduces SHOT, a source hypothesis transfer method for unsupervised domain adaptation that does not require access to source data, achieving state-of-the-art results across various adaptation scenarios.

Contribution

The paper proposes a novel framework called SHOT that leverages only a trained source model for unsupervised domain adaptation, eliminating the need for source data.

Findings

SHOT achieves state-of-the-art performance on multiple benchmarks.

It effectively handles closed-set, partial-set, and open-set domain adaptation.

The method is versatile and practical for privacy-sensitive scenarios.

Abstract

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named \emph{Source HypOthesis Transfer} (SHOT). SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. To verify its versatility, we evaluate SHOT in a variety of adaptation cases including closed-set, partial-set, and open-set domain adaptation. Experiments indicate that SHOT yields state-of-the-art results among multiple domain adaptation benchmarks.