A source-free domain adaptation method using intra-image Shuffle PatchMix augmentation and confidence-margin weighted pseudo-labels reports state-of-the-art accuracy on PACS, VisDA-C, and DomainNet-126.
Experimental results demonstrate that the proposed approach outperforms state-of-the-art methods across three benchmark datasets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
A source-free domain adaptation method using intra-image Shuffle PatchMix augmentation and confidence-margin weighted pseudo-labels reports state-of-the-art accuracy on PACS, VisDA-C, and DomainNet-126.