Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation via Discriminative Manifold Propagation
You-Wei Luo, Chuan-Xian Ren, Dao‐Qing Dai, Hong Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add manifold metric alignment loss (ablation) | DMP · VisDA-2017 (vanilla) | accuracy (%): 69.7 -> 79.3 | Improved |
| add discriminative structure loss (ablation) | DMP · VisDA-2017 (vanilla) | accuracy (%): 71.1 -> 79.3 | Improved |
| add manifold metric alignment loss (ablation) | DMP · Office-31 (vanilla) | accuracy (%): 84.1 -> 87.4 | Improved |
| add discriminative structure loss (ablation) | DMP · Office-31 (vanilla) | accuracy (%): 82.3 -> 87.4 | Improved |
| add manifold metric alignment loss (ablation) | DMP · Office-Home (vanilla) | accuracy (%): 67.1 -> 68.1 | Improved |
| add discriminative structure loss (ablation) | DMP · Office-Home (vanilla) | accuracy (%): 66.3 -> 68.1 | Improved |
| add manifold metric alignment loss (ablation) | DMP · ImageCLEF (vanilla) | accuracy (%): 87.3 -> 89.1 | Improved |
| add discriminative structure loss (ablation) | DMP · ImageCLEF (vanilla) | accuracy (%): 86.8 -> 89.1 | Improved |
| use affine Grassmann instead of Grassmann manifold (partial setting) (ablation) | DMP · ImageCLEF (partial) | accuracy (%): 90.5 -> 87.9 | Hurt |
| use Log-Euclidean instead of Grassmann manifold (partial setting) (ablation) | DMP · ImageCLEF (partial) | accuracy (%): 90.5 -> 88.9 | Hurt |
| vary manifold type among Grassmann, affine Grassmann, Log-Euclidean (vanilla) (ablation) | DMP · ImageCLEF (vanilla) | accuracy (%): 89.1, 88.9, 89.1 | No clear effect |
| add entropy term to DMP for partial UDA | DMP+ent · Office-Home (partial) | accuracy (%): 66.5 -> 73.5 | Improved |
Closest papers by meaning
- Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment (AAAI 2020 · similarity 0.99)
- Unsupervised Domain Adaptation With Similarity Learning (CVPR 2018 · similarity 0.90)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Unsupervised Domain Adaptation for Distance Metric Learning (ICLR 2019 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.88)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 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.
