Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
This work addresses domain adaptation without access to source data, offering a simple and effective solution for scenarios where data privacy or availability is limited.
The paper tackles source-free domain adaptation by treating it as an unsupervised clustering problem, proposing a method that optimizes prediction consistency to achieve efficient feature clustering and assignment, with experimental results demonstrating its superiority and applicability as a baseline.
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.