Research map / Label-efficient and robust learning / Domain adaptation and generalization
Information-Theoretic Domain Adaptation Under Severe Noise Conditions
Wei Wang, Hao Wang, Zhi-Yong Ran, Ran He
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 |
|---|---|---|---|
| correntropy-based robust adaptation (RIDA) vs l1-norm DTSL | RIDA · CMU-PIE with occlusions, mean | classification accuracy (%): 49.57 -> 54.81 | Improved |
| RIDA vs DTSL on original CMU-PIE | RIDA · CMU-PIE original, mean | classification accuracy (%): 63.53 -> 66.73 | Improved |
| RIDA vs best non-robust transfer method JDA | RIDA · CMU-PIE original, mean | classification accuracy (%): 60.24 -> 66.73 | Improved |
| RIDA vs non-transfer CESR | RIDA · CMU-PIE with occlusions, mean | classification accuracy (%): 48.18 -> 54.81 | Improved |
| RIDA vs 1-NN on COIL-20 original C1 vs C2 | RIDA · COIL-20 original, C1 vs C2 | classification accuracy (%): 83.61 -> 89.17 | Improved |
| RIDA vs JDA on COIL-20 original C1 vs C2 | RIDA · COIL-20 original, C1 vs C2 | classification accuracy (%): 89.31 -> 89.17 | No clear effect |
| RIDA vs DTSL on COIL-20 original C2 vs C1 | RIDA · COIL-20 original, C2 vs C1 | classification accuracy (%): 89.17 -> 88.06 | Hurt |
| RIDA vs CESR on P2 vs P4 (similar distributions) | RIDA · CMU-PIE original, P2 vs P4 | classification accuracy (%): 84.53 -> 80.29 | Hurt |
| RIDA vs DTSL on P4 vs P3 | RIDA · CMU-PIE original, P4 vs P3 | classification accuracy (%): 82.23 -> 91.12 | Improved |
| RIDA vs DTSL on P2 vs P4 | RIDA · CMU-PIE original, P2 vs P4 | classification accuracy (%): 71.43 -> 80.29 | Improved |
| add 50% contiguous occlusions (monkey image) to target data | JDA · CMU-PIE mean | classification accuracy (%): 60.24 -> 36.14 | Hurt |
| add occlusions to target data | RIDA · CMU-PIE mean | classification accuracy (%): 66.73 -> 54.81 | Hurt |
Closest papers by meaning
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.85)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.84)
- Adaptive Domain Learning for Cross-domain Image Denoising (NeurIPS 2024 · similarity 0.84)
- Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models (ICML 2024 · similarity 0.84)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.84)
- Proxy Denoising for Source-Free Domain Adaptation (ICLR 2025 · similarity 0.84)
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.
