Research map / Label-efficient and robust learning / Domain adaptation and generalization
Re-Energizing Domain Discriminator With Sample Relabeling for Adversarial Domain Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
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 dynamic relabeling of well-aligned target samples (no mixup) (ablation) | DANN · VisDA-2017 | accuracy: 61.23 -> 65.91 | Improved |
| add dynamic relabeling of well-aligned target samples (no mixup) (ablation) | CDAN · VisDA-2017 | accuracy: 70.82 -> 75.62 | Improved |
| add dynamic relabeling (no mixup) (ablation) | DANN · Office-31 | accuracy: 83.42 -> 85.24 | Improved |
| add dynamic relabeling (no mixup) (ablation) | CDAN · Office-31 | accuracy: 87.90 -> 89.58 | Improved |
| add mixup within the updated source set (ablation) | DANN+RADA · Office-31 | accuracy: 85.24 -> 86.79 | Improved |
| add mixup within the updated source set (ablation) | CDAN+RADA · VisDA-2017 | accuracy: 75.62 -> 76.28 | Improved |
| add mixup within the updated source set (ablation) | CDAN+RADA · Office-Home | accuracy: 70.25 -> 71.37 | Improved |
| replace entropy re-weighting variants by RADA relabeling | DANN · Digit-Five multi-source | accuracy: 86.1 -> 91.5 | Improved |
| vary threshold tau (ablation) | DANN/CDAN+RADA w/o MU · VisDA-2017 | accuracy | No clear effect |
| vary patience K (ablation) | DANN/CDAN+RADA w/o MU · VisDA-2017 | accuracy | No clear effect |
| add RADA to CDAN | CDAN · Digit-Five multi-source | accuracy: 88.7 -> 93.2 | Improved |
| add RADA to CDAN | CDAN · DomainNet | accuracy: 45.2 -> 47.5 | Improved |
Closest papers by meaning
- Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.91)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.91)
- Mind the Discriminability: Asymmetric Adversarial Domain Adaptation (ECCV 2020 · similarity 0.90)
- Adversarial Unsupervised Domain Adaptation With Conditional and Label Shift: Infer, Align and Iterate (ICCV 2021 · similarity 0.89)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.88)
- On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning (AAAI 2024 · 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.
