Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain-Specific Bias Filtering for Single Labeled Domain Generalization
Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Qing Wu, Lanfen Lin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add feature extractor debiasing (L_IM and L_CU) and classifier rectification to ERM (ablation) | DSBF · PACS SLDG | average accuracy (%): 61.11 -> 67.12 | Improved |
| add feature extractor debiasing (L_IM and L_CU) and classifier rectification to ERM (ablation) | DSBF · Office-Home SLDG | average accuracy (%): 53.62 -> 56.40 | Improved |
| add classifier rectification only (no debiasing) (ablation) | DSBF · PACS SLDG | average accuracy (%): 61.11 -> 61.47 | No clear effect |
| add L_CU to rectification (ablation) | DSBF · PACS SLDG | average accuracy (%): 61.47 -> 65.34 | Improved |
| add L_IM to rectification (ablation) | DSBF · PACS SLDG | average accuracy (%): 61.47 -> 65.75 | Improved |
| add classifier rectification losses L_FP and L_BF on top of debiasing (ablation) | DSBF · PACS SLDG | average accuracy (%): 65.99 -> 66.99 | Improved |
| add inter-domain attention module (ablation) | DSBF · PACS SLDG | average accuracy (%): 66.99 -> 67.12 | Improved |
| add inter-domain attention module (ablation) | DSBF · Office-Home SLDG | average accuracy (%): 55.97 -> 56.40 | Improved |
| use clustering pseudo labels instead of direct model predictions (ablation) | DSBF · PACS SLDG | average accuracy (%): 58.28 -> 67.12 | Improved |
| increase clustering iterations from 1 to 3 (ablation) | DSBF · PACS SLDG | average accuracy (%): 67.12 -> 67.51 | No clear effect |
| increase clustering iterations from 1 to 3 (ablation) | DSBF · Office-Home SLDG | average accuracy (%): 56.40 -> 56.02 | Hurt |
| add unlabeled source domains rather than using only labeled source (DSBF vs ERM) | DSBF · DomainNet SLDG | average accuracy (%): 34.45 -> 38.15 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 2024 · similarity 0.90)
- Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap (ICLR 2025 · similarity 0.89)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.88)
- Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization (NeurIPS 2025 · similarity 0.88)
- Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization (CVPR 2025 · similarity 0.88)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
