Research map / Label-efficient and robust learning / Domain adaptation and generalization
Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 NWD regularization to DANN | DANN · Office-Home | accuracy: 57.6 -> 65.5 | Helped |
| Add NWD regularization to DANN | DANN · VisDA-2017 | accuracy: 22.6% | Helped |
| Add NWD regularization to CDAN | CDAN · VisDA-2017 | accuracy: 7.5% | Helped |
| Add NWD regularization to MDD | MDD · VisDA-2017 | accuracy: 5.2% | Helped |
| Add NWD regularization to MCC | MCC · VisDA-2017 | accuracy: 4.9% | Helped |
| Add NWD regularization to CDAN | CDAN · Office-31 | accuracy | Mixed |
| Add NWD regularization to MCC | MCC · ImageCLEF-2014 | accuracy: 89.3 -> 90.7 | Helped |
| Reuse the task-specific classifier as the discriminator and use NWD for alignment | DALN · Office-Home | accuracy: 71.3 -> 71.8 | Helped |
Closest papers by meaning
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.91)
- Discriminative Adversarial Domain Adaptation (AAAI 2020 · similarity 0.91)
- Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.91)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.90)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.88)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (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.