Research map / Label-efficient and robust learning / Semi-supervised learning
Memory Oriented Transfer Learning for Semi-Supervised Image Deraining
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 |
|---|---|---|---|
| Add unlabeled real-world data to training alongside labeled synthetic data | MOSS · DDN-SIRR synthetic test, Dense | PSNR: 20.29 -> 22.36 | Helped |
| Add unlabeled real-world data to training alongside labeled synthetic data | MOSS · DDN-SIRR synthetic test, Sparse | PSNR: 25.90 -> 27.78 | Helped |
| Add unlabeled data to training with 10% labeled data | MOSS · Rain200H | PSNR: 25.76 -> 26.06 | Helped |
| Add unlabeled data to training with 10% labeled data | MOSS · Rain800 | PSNR: 23.28 -> 23.79 | Helped |
| Add a self-supervised memory module for rain patterns (ablation) | MOSS · DDN-SIRR Dense | PSNR: 22.21 -> 22.91 | Helped |
| Add a self-supervised memory module for rain patterns (ablation) | MOSS · DDN-SIRR Sparse | PSNR: 26.82 -> 27.78 | Helped |
| Add the self-training mechanism (ablation) | MOSS · DDN-SIRR Dense | PSNR: 20.99 -> 22.91 | Helped |
| Add the self-training mechanism (ablation) | MOSS · DDN-SIRR Sparse | PSNR: 25.83 -> 27.78 | Helped |
| Add the Total Variation regularizer (ablation) | MOSS · DDN-SIRR Dense | PSNR: 22.68 -> 22.91 | Helped |
| Add the Total Variation regularizer (ablation) | MOSS · DDN-SIRR Sparse | PSNR: 27.58 -> 27.78 | Helped |
| Add the encoder-decoder skip-connection (ablation) | MOSS · DDN-SIRR Dense | PSNR: 22.00 -> 22.91 | Helped |
| Add the encoder-decoder skip-connection (ablation) | MOSS · DDN-SIRR Sparse | PSNR: 26.80 -> 27.78 | Helped |
Closest papers by meaning
- Semi-Supervised Transfer Learning for Image Rain Removal (CVPR 2019 · similarity 0.93)
- Multi-Decoding Deraining Network and Quasi-Sparsity Based Training (CVPR 2021 · similarity 0.91)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.89)
- Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining (CVPR 2025 · similarity 0.89)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.89)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.89)
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.