基于置信度加权伪标签的Shuffle PatchMix增强方法用于提升无源域适应性能

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

May 30, 2025

作者: Prasanna Reddy Pulakurthi, Majid Rabbani, Jamison Heard, Sohail Dianat, Celso M. de Melo, Raghuveer Rao

cs.AI

摘要

本研究探讨了无源域适应（Source-Free Domain Adaptation, SFDA）问题，即在无法访问源数据的情况下，模型如何适应目标域。为此，我们引入了一种新的增强技术——混洗补丁混合（Shuffle PatchMix, SPM）以及一种创新的重加权策略，以提升模型性能。SPM通过混洗并融合图像补丁，生成多样且具有挑战性的增强样本，而重加权策略则优先考虑可靠的伪标签，从而减轻标签噪声的影响。这些技术在处理较小数据集（如PACS）时尤为有效，因为这类数据集更容易出现过拟合和伪标签噪声问题。我们在三大主流基准测试——PACS、VisDA-C和DomainNet-126上取得了最先进的成果。特别是在PACS数据集上，单目标和多目标设置下的准确率分别提升了7.3%（从79.4%增至86.7%）和7.2%，而在DomainNet-126和VisDA-C上则分别实现了2.8%和0.7%的提升。这种结合先进增强技术与稳健伪标签重加权的方法，为SFDA设立了新的基准。相关代码已发布于：https://github.com/PrasannaPulakurthi/SPM。

English

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