Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation

TL;DR

This paper introduces Shuffle PatchMix, an augmentation technique combined with confidence-margin based pseudo-label reweighting, significantly improving source-free domain adaptation performance across multiple benchmarks.

Contribution

It proposes Shuffle PatchMix and a reweighting strategy for pseudo-labels, advancing SFDA by reducing overfitting and label noise, and setting new state-of-the-art results.

Findings

Achieved 7.3% improvement on PACS benchmark

Enhanced performance on DomainNet-126 and VisDA-C datasets

Effective especially on smaller datasets like PACS

Abstract

This work investigates Source-Free Domain Adaptation (SFDA), where a model adapts to a target domain without access to source data. A new augmentation technique, Shuffle PatchMix (SPM), and a novel reweighting strategy are introduced to enhance performance. SPM shuffles and blends image patches to generate diverse and challenging augmentations, while the reweighting strategy prioritizes reliable pseudo-labels to mitigate label noise. These techniques are particularly effective on smaller datasets like PACS, where overfitting and pseudo-label noise pose greater risks. State-of-the-art results are achieved on three major benchmarks: PACS, VisDA-C, and DomainNet-126. Notably, on PACS, improvements of 7.3% (79.4% to 86.7%) and 7.2% are observed in single-target and multi-target settings, respectively, while gains of 2.8% and 0.7% are attained on DomainNet-126 and VisDA-C. This combination of advanced augmentation and robust pseudo-label reweighting establishes a new benchmark for SFDA. The code is available at: https://github.com/PrasannaPulakurthi/SPM