基於置信度邊界加權偽標籤的Shuffle PatchMix增強方法，用於提升無源域適應性能

摘要

本研究探討了無源域適應（Source-Free Domain Adaptation, SFDA）問題，即在無法取得源域數據的情況下，使模型適應目標域。為提升性能，我們引入了一種新的數據增強技術——混洗拼貼混合（Shuffle PatchMix, SPM），以及一種新穎的重新加權策略。SPM通過混洗並融合圖像塊來生成多樣且具挑戰性的增強數據，而重新加權策略則優先考慮可靠的偽標籤，以減輕標籤噪聲的影響。這些技術在如PACS等較小數據集上尤為有效，因為這些數據集更容易出現過擬合和偽標籤噪聲問題。我們在三大基準測試——PACS、VisDA-C和DomainNet-126上取得了領先的成果。特別是在PACS數據集上，單目標和多目標設置下的準確率分別提升了7.3%（從79.4%到86.7%）和7.2%，而在DomainNet-126和VisDA-C上則分別獲得了2.8%和0.7%的提升。這種結合先進數據增強與穩健偽標籤重新加權的方法，為SFDA設立了新的基準。相關代碼已公開於：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

基於置信度邊界加權偽標籤的Shuffle PatchMix增強方法，用於提升無源域適應性能

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

摘要

Support