Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
prasannareddypAbstract
A new augmentation technique, Shuffle PatchMix, and a reweighting strategy improve performance in source-free domain adaptation, achieving state-of-the-art results on PACS, VisDA-C, and DomainNet-126 benchmarks.
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
Community
🤔 No image labels in your target domain? No problem! Our paper, “Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation,” directly addresses this challenging scenario.
This work has been accepted to ICIP 2025.
Key Innovations:
- Shuffle PatchMix (SPM): A new augmentation method that creates diverse and challenging image variations to enhance data diversity and improve model robustness and generalization.
- Confidence-Margin Reweighting: A novel pseudo-label reweighting strategy that mitigates label noise by selectively emphasizing reliable pseudo-labels, resulting in faster and more stable adaptation.
Highlights:
- Sets a new state-of-the-art on three benchmark datasets (PACS, VisDA-C, and DomainNet-126).
- Particularly effective on small-scale datasets, outperforming the previous best by +7.3 pp.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data (2025)
- Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation (2025)
- Improving Out-of-Domain Robustness with Targeted Augmentation in Frequency and Pixel Spaces (2025)
- SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation (2025)
- Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation (2025)
- Certainty and Uncertainty Guided Active Domain Adaptation (2025)
- Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 3
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper