Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Transfer Learning for Image Rain Removal
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 |
|---|---|---|---|
| Train with real unsupervised rainy images in addition to synthetic supervised pairs | CNN rain removal · Dense synthetic rain | PSNR: 19.90 -> 21.60 | Helped |
| Train with real unsupervised rainy images in addition to synthetic supervised pairs | CNN rain removal · Sparse synthetic rain | PSNR: 26.88 -> 26.98 | Helped |
| Add the unsupervised real-rain loss rather than using supervised training alone (ablation) | CNN rain removal · Validation data in a different rain domain | PSNR | Helped |
| Increase the unsupervised loss weight from 0 to 0.2 or 1 (ablation) | CNN rain removal · Supervised training domain | PSNR | Mixed |
| Use more supervised training patches without unsupervised transfer (ablation) | Supervised CNN · Validation data in a different rain domain | PSNR | Hurt |
Closest papers by meaning
- Memory Oriented Transfer Learning for Semi-Supervised Image Deraining (CVPR 2021 · similarity 0.93)
- A Model-Driven Deep Neural Network for Single Image Rain Removal (CVPR 2020 · similarity 0.91)
- From Rain Generation to Rain Removal (CVPR 2021 · similarity 0.91)
- Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective (AAAI 2019 · similarity 0.90)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.88)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.88)
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.