Research map / Label-efficient and robust learning / Domain adaptation and generalization
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu
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 FAA on supervised source loss only (FAA-S) (ablation) | self-training (ST) · GTA5 to Cityscapes | mIoU: 42.6 -> 47.8 | Improved |
| add FAA on unsupervised target loss only (FAA-T) (ablation) | self-training (ST) · GTA5 to Cityscapes | mIoU: 42.6 -> 48.5 | Improved |
| add FAA on both source and target losses vs FAA-T only (ablation) | self-training (ST) · GTA5 to Cityscapes | mIoU: 48.5 -> 50.1 | Improved |
| add FAA on both losses vs FAA-T only (ablation) | AdaptSeg · GTA5 to Cityscapes | mIoU: 47.1 -> 48.0 | Improved |
| add FAA to supervised-only baseline | source-only baseline · GTA5 to Cityscapes | mIoU: 36.6 -> 45.2 | Improved |
| add FAA | CRST · SYNTHIA to Cityscapes | mIoU*: 50.1 -> 55.9 | Improved |
| add FAA | CRST · VisDA17 | mean accuracy: 78.1 -> 82.7 | Improved |
| add FAA | TAT · Office-31 | mean accuracy: 88.4 -> 90.3 | Improved |
| add FAA | SWDA · Cityscapes to Foggy Cityscapes | mAP: 34.3 -> 38.3 | Improved |
| add FAA | CRDA · Cityscapes to BDD100k | mAP: 26.9 -> 29.9 | Improved |
| add dropout to self-training (ablation) | ST · GTA5 to Cityscapes | mIoU: 42.6 -> 43.1 | Improved |
| add mixup to self-training (ablation) | ST · GTA5 to Cityscapes | mIoU: 42.6 -> 43.6 | Improved |
Closest papers by meaning
- Adversarial Robustness for Unsupervised Domain Adaptation (ICCV 2021 · similarity 0.91)
- Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm (IJCV 2025 · similarity 0.91)
- Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks (TPAMI 2021 · similarity 0.91)
- Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation (ICCV 2023 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.88)
- Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.88)
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.
