Research map / Label-efficient and robust learning / Semi-supervised learning
ART-SS: An Adaptive Rejection Technique for Semi-Supervised Restoration for Adverse Weather-Affected Images
Rajeev Yasarla, Carey E. Priebe, Vishal M. Patel
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 ART-SS rejection of unlabeled images | SIRR · DDN-SIRR dense rain | PSNR: 21.60 -> 22.16 | Improved |
| add ART-SS rejection of unlabeled images | Syn2Real · DDN-SIRR dense rain | PSNR: 22.36 -> 22.67 | Improved |
| add ART-SS rejection of unlabeled images | MOSS · DDN-SIRR dense rain | PSNR: 22.91 -> 23.32 | Improved |
| add ART-SS rejection of unlabeled images | MOSS · DDN-SIRR sparse rain | PSNR: 27.78 -> 28.16 | Improved |
| add ART-SS rejection of unlabeled images | DAID · SOTS dehazing | PSNR: 27.76 -> 29.15 | Improved |
| add ART-SS rejection of unlabeled images | Li et al. · HazeRD dehazing | PSNR: 16.55 -> 18.17 | Improved |
| add ART-SS in cross-domain transfer Rain1400 to Rain800 | SIRR · Rain1400 -> Rain800 | PSNR: 22.62 -> 23.42 | Improved |
| add ART-SS in cross-domain transfer Rain800 to Rain1400 | SIRR · Rain800 -> Rain1400 | PSNR: 26.17 -> 26.98 | Improved |
| use all unlabeled target images without rejection (NR) vs source only (ablation) | Syn2Real · Rain800 -> SPA-data | PSNR: 31.36 -> 34.16 | Improved |
| replace random sampling of unlabeled images with ART-SS (ablation) | Syn2Real · Rain800 -> SPA-data | PSNR: 34.94 -> 37.28 | Improved |
| replace similarity-only rejection with ART-SS (adds uncertainty-weighted threshold) (ablation) | Syn2Real · Rain800 -> SPA-data | PSNR: 35.99 -> 37.28 | Improved |
| replace similarity-only rejection with ART-SS (ablation) | MOSS · Rain800 -> SPA-data | PSNR: 35.86 -> 37.56 | Improved |
Closest papers by meaning
- Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions (CVPR 2023 · similarity 0.90)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.88)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.87)
- Learning Real-World Image De-weathering with Imperfect Supervision (AAAI 2024 · similarity 0.87)
- Language-driven All-in-one Adverse Weather Removal (CVPR 2024 · similarity 0.86)
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (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.
