Research map / Label-efficient and robust learning / Domain adaptation and generalization
Enhanced Transport Distance 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 |
|---|---|---|---|
| Use ETD instead of CDAN+E | ResNet-50 UDA · Office-31 average | accuracy: 87.7 -> 86.2 | Hurt |
| Use ETD instead of CDAN+E | ResNet-50 UDA · ImageCLEF-DA average | accuracy: 87.7 -> 89.7 | Helped |
| Use ETD instead of CDAN+E | ResNet-50 UDA · Office-Home average | accuracy: 65.8 -> 67.3 | Helped |
| Use ETD instead of CyCADA | ResNet-50 digit adaptation · Digits Recognition average | accuracy: 94.2 -> 96.9 | Helped |
| Add attention to stacked OT with target entropy (ablation) | ETD · ImageCLEF-DA P→I | accuracy: 91.0 -> 92.0 | Helped |
| Add attention to stacked OT with target entropy (ablation) | ETD · ImageCLEF-DA P→C | accuracy: 94.4 -> 95.2 | Helped |
| Add attention to stacked OT with target entropy (ablation) | ETD · ImageCLEF-DA I→C | accuracy: 95.8 -> 95.2 | Hurt |
| Add attention to stacked OT with target entropy (ablation) | ETD · ImageCLEF-DA I→P | accuracy: 78.4 -> 78.2 | Hurt |
| Use the Kantorovich potential network instead of stacked OT, with target entropy (ablation) | ETD · ImageCLEF-DA | accuracy: The paper reports improvements of 0.5%∼1.0% almost on all tasks. | Helped |
| Add attention to the Kantorovich potential network with target entropy (ablation) | ETD · ImageCLEF-DA I→C | accuracy: 96.22 -> 98.0 | Helped |
| Add attention to the Kantorovich potential network with target entropy (ablation) | ETD · ImageCLEF-DA I→P | accuracy: 78.5 -> 81.0 | Helped |
| Add attention to the Kantorovich potential network with target entropy (ablation) | ETD · ImageCLEF-DA P→C | accuracy: 94.5 -> 95.0 | Helped |
Closest papers by meaning
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.89)
- COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport (CVPR 2023 · similarity 0.89)
- Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation (CVPR 2020 · similarity 0.89)
- Prototypical Partial Optimal Transport for Universal Domain Adaptation (AAAI 2023 · similarity 0.89)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.88)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.87)
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.