Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity

TL;DR

This paper introduces a novel source-free domain adaptation method that optimizes batch-wise cosine similarity to improve clustering and reduce noise, outperforming existing approaches on challenging datasets.

Contribution

It proposes a new loss function based on batch-wise cosine similarity and neighborhood signature to enhance adaptation without source data.

Findings

Outperforms existing methods on VisDA dataset

Achieves competitive results on multiple benchmarks

Uses a single loss term for effective adaptation

Abstract

Source-Free Domain Adaptation (SFDA) is an emerging area of research that aims to adapt a model trained on a labeled source domain to an unlabeled target domain without accessing the source data. Most of the successful methods in this area rely on the concept of neighborhood consistency but are prone to errors due to misleading neighborhood information. In this paper, we explore this approach from the point of view of learning more informative clusters and mitigating the effect of noisy neighbors using a concept called neighborhood signature, and demonstrate that adaptation can be achieved using just a single loss term tailored to optimize the similarity and dissimilarity of predictions of samples in the target domain. In particular, our proposed method outperforms existing methods in the challenging VisDA dataset while also yielding competitive results on other benchmark datasets.