Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Adaptation With Auxiliary Target Domain-Oriented Classifier
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 ATDOC-NA rather than ordinary pseudo-labeling | Office-31 UDA · Office-31 UDA | average accuracy: 84.7 -> 89.7 | Helped |
| Use ATDOC-NA pseudo-labels in MixMatch | VisDA-C · VisDA-C validation | mean accuracy: 70.4 -> 86.3 | Helped |
| Add ATDOC-NA to CDAN+E | Office-Home closed-set UDA · Office-Home closed-set UDA | average accuracy: 68.5 -> 73.2 | Helped |
| Add confidence weighting to ATDOC-NA (ablation) | ATDOC-NA · Office-31 UDA | average accuracy: 89.4 -> 89.7 | Helped |
| Add confidence weighting to ATDOC-NA (ablation) | ATDOC-NA · VisDA-C validation | mean accuracy: 79.2 -> 80.3 | Helped |
| Use prediction sharpening temperature T=0.5 rather than T=1 (ablation) | ATDOC-NA · Office-31 UDA | average accuracy: 85.8 -> 89.7 | Helped |
| Use prediction sharpening temperature T=0.5 rather than T=1 (ablation) | ATDOC-NA · VisDA-C validation | mean accuracy: 65.6 -> 80.3 | Helped |
| Include source features in the target memory (ablation) | ATDOC-NA · Office-31 UDA | average accuracy: 89.7 -> 89.4 | Hurt |
| Include source features in the target memory (ablation) | ATDOC-NA · VisDA-C validation | mean accuracy: 80.3 -> 80.9 | Helped |
| Use the default neighborhood size m=5 rather than m=1 or m=3 (ablation) | ATDOC-NA · Office-31 UDA | average accuracy: 84.7 -> 89.7; 87.9 -> 89.7 | Helped |
| Use the default neighborhood size m=5 rather than m=1 or m=3 (ablation) | ATDOC-NA · VisDA-C validation | mean accuracy: 79.9 -> 80.3; 80.0 -> 80.3 | Helped |
| Set λ=0.1 instead of the default λ=0.2 (ablation) | ATDOC-NA · Office-31 UDA | average accuracy: 89.7 -> 90.2 | Helped |
Closest papers by meaning
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · similarity 0.89)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.88)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 2025 · similarity 0.87)
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.86)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · 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.