Research map / Label-efficient and robust learning / Domain adaptation and generalization
Reliable Weighted Optimal Transport for Unsupervised 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 |
|---|---|---|---|
| Apply RWOT instead of CDAN | ResNet-50 UDA · Office-31 | accuracy: 87.7 -> 90.8 | Helped |
| Apply RWOT instead of CDAN | ResNet-50 UDA · ImageNet-Caltech | accuracy: 94.5 -> 95.3 | Helped |
| Apply RWOT instead of TPN | ResNet-50 UDA · VisDA-2017 | accuracy: 80.4 -> 84.0 | Helped |
| Apply RWOT instead of DeepJDOT | LeNet UDA · Digits | accuracy: 96.4 -> 98.3 | Helped |
| Add intra-domain structure to SSR alongside spatial prototypical information (ablation) | RWOT weighted optimal transport · Office-31 | accuracy: 89.6 -> 90.8 | Helped |
| Add spatial prototypical information to SSR alongside intra-domain structure (ablation) | RWOT weighted optimal transport · Office-31 | accuracy: 88.5 -> 90.8 | Helped |
| Add discriminative centroid loss (ablation) | RWOT · Office-31 | accuracy: 90.4 -> 90.8 | Helped |
| Add intra-domain structure to SSR alongside spatial prototypical information (ablation) | RWOT weighted optimal transport · Digits | accuracy: 97.7 -> 98.3 | Helped |
| Add spatial prototypical information to SSR alongside intra-domain structure (ablation) | RWOT weighted optimal transport · Digits | accuracy: 97.1 -> 98.3 | Helped |
| Add discriminative centroid loss (ablation) | RWOT · Digits | accuracy: 98.1 -> 98.3 | Helped |
Closest papers by meaning
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.89)
- Joint distribution optimal transportation for domain adaptation (NeurIPS 2017 · similarity 0.89)
- Enhanced Transport Distance for Unsupervised Domain Adaptation (CVPR 2020 · similarity 0.89)
- Prototypical Partial Optimal Transport for Universal Domain Adaptation (AAAI 2023 · similarity 0.89)
- COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport (CVPR 2023 · similarity 0.88)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (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.