Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bridging Theory and Algorithm for 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 MDD instead of CDAN | ResNet-50 domain adaptation · Office-31 | accuracy (%): 87.7 -> 88.9 | Helped |
| use MDD instead of CDAN | ResNet-50 domain adaptation · Office-Home | accuracy (%): 65.8 -> 68.1 | Helped |
| use MDD instead of CDAN | ResNet-50 domain adaptation · VisDA-2017 Synthetic → Real | accuracy (%): 70.0 -> 74.6 | Helped |
| increase the margin factor from γ=1 to γ=4 (ablation) | MDD · Office-31 | accuracy (%): 87.6 -> 88.9 | Helped |
| increase the margin factor from γ=4 to γ=5 (ablation) | MDD · Office-31 | accuracy (%): 88.9 -> 88.7 | Hurt |
| increase the margin factor from γ=4 to γ=6 (ablation) | MDD · Office-31 | accuracy (%): 88.9 -> 88.6 | Hurt |
Closest papers by meaning
- Margin-aware Adversarial Domain Adaptation with Optimal Transport (ICML 2020 · similarity 0.91)
- f-Domain Adversarial Learning: Theory and Algorithms (ICML 2021 · similarity 0.91)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.91)
- Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.90)
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.90)
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.