通过打乱拼接增强与置信度加权伪标签，提升无源域自适应性能
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
- 打乱图像块混合生成多样化增强数据，提升泛化能力
- 在PACS数据集上单目标/多目标设置分别提升7.3%和7.2%
- 适合小样本场景下无源域自适应任务的研究与应用
本文研究无源域自适应（SFDA），即模型在无法访问源数据的情况下适配目标域。提出新增强方法Shuffle PatchMix（SPM）和伪标签重加权策略：SPM通过打乱并混合图像块生成更具挑战性的增强数据；重加权策略优先选择可信伪标签，降低标签噪声影响。该方法在较小数据集如PACS上表现尤为突出，有效缓解过拟合与伪标签噪声问题。在三个主流基准测试中均达到最新水平：在PACS上，单目标设置准确率从79.4%提升至86.7%（+7.3%），多目标设置提升7.2%；在DomainNet-126和VisDA-C上分别提升2.8%和0.7%。结合先进增强与鲁棒伪标签重加权，建立新的SFDA基准。代码已开源。
原文摘要 · Abstract (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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。