Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

TL;DR

This paper introduces a simple, effective source-free domain adaptation method based on prediction consistency in feature space, leading to improved clustering and adaptability without source data.

Contribution

It proposes a novel prediction consistency objective for SFDA, relating existing methods through discriminability and diversity, and demonstrates strong empirical results.

Findings

Outperforms existing SFDA methods in experiments

Can be adapted to open-set and partial-set domain adaptation

Serves as a strong baseline for future SFDA research

Abstract

We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency. This objective encourages local neighborhood features in feature space to have similar predictions while features farther away in feature space have dissimilar predictions, leading to efficient feature clustering and cluster assignment simultaneously. For efficient training, we seek to optimize an upper-bound of the objective resulting in two simple terms. Furthermore, we relate popular existing methods in domain adaptation, source-free domain adaptation and contrastive learning via the perspective of discriminability and diversity. The experimental results prove the superiority of our method, and our method can be adopted as a simple but strong baseline for future research in SFDA. Our method can be also adapted to source-free open-set and partial-set DA which further shows the generalization ability of our method. Code is available in https://github.com/Albert0147/AaD_SFDA.