Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
Read the paperCheck 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 |
|---|---|---|---|
| Use BCDM instead of the source-only ResNet-101 model | VisDA-2017 adaptation · VisDA-2017 | accuracy (Avg.): 31.0% | Helped |
| Use BCDM instead of MCD | Bi-classifier adaptation · VisDA-2017 | accuracy (Avg.): 11.5% | Helped |
| Use BCDM instead of SWD | Bi-classifier adaptation · VisDA-2017 | accuracy (Avg.): 7.0% | Helped |
| Use BCDM instead of NoAdaptation | Semantic segmentation adaptation · GTA5 → Cityscapes validation | mIoU: 10.0% | Helped |
| Add CDD to STAR in place of the baseline ℓ1 metric | STAR · Office-31 | accuracy (Avg.): 1.4 ↑ | Helped |
| Use CDD instead of SWD | STAR · Office-31 | accuracy (Avg.): 88.2 -> 89.2 | Helped |
Closest papers by meaning
- Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.90)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.89)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.88)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.88)
- A Separation and Alignment Framework for Black-Box Domain Adaptation (AAAI 2024 · similarity 0.86)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.86)
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.