Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation. (arXiv:2205.04183v2 [cs.CV] UPDATED)

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, …

arxiv cv domain adaptation free