Research map / Continual learning / Online and replay-based
Image De-Raining via Continual Learning
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 PIGWM to sequential PreNet training | PreNet · Rain100H after Rain100H→Rain100L training | PSNR: 18.97 -> 28.08 | Helped |
| Add PIGWM to sequential PreNet training | PreNet · Rain100L after Rain100H→Rain100L training | PSNR: 38.29 -> 36.95 | Hurt |
| Add PIGWM to sequential SASI training | SASI · Rain100H after Rain100H→Rain100L training | PSNR: 19.42 -> 29.76 | Helped |
| Add PIGWM to sequential SASI training | SASI · Rain100L after Rain100H→Rain100L training | PSNR: 37.40 -> 36.73 | Hurt |
| Add PIGWM to sequential ID-CGAN training | ID-CGAN · Rain800 after Rain800→Rain100L training | PSNR: 20.57 -> 23.36 | Helped |
| Add PIGWM to sequential ID-CGAN training | ID-CGAN · Rain100L after Rain800→Rain100L training | PSNR: 25.56 -> 24.13 | Hurt |
| Add PIGWM to sequential ID-CGAN training | ID-CGAN · Rain800 after Rain800→Rain100H training | PSNR: 19.89 -> 23.08 | Helped |
| Add PIGWM to sequential ID-CGAN training | ID-CGAN · Rain100H after Rain800→Rain100H training | PSNR: 13.25 -> 11.16 | Hurt |
| Add PIGWM to three-dataset sequential training | PreNet · Rain100H after Rain100H→Rain100L→Rain1400 training | PSNR: 15.31 -> 28.18 | Helped |
| Add PIGWM to three-dataset sequential training | PreNet · Rain100L after Rain100H→Rain100L→Rain1400 training | PSNR: 28.88 -> 36.85 | Helped |
| Add PIGWM to three-dataset sequential training | PreNet · Rain1400 after Rain100H→Rain100L→Rain1400 training | PSNR: 31.90 -> 28.06 | Hurt |
| Increase the importance-regularization coefficient λ from 0 to 10 (ablation) | PreNet + PIGWM · Rain100H, sequential Rain100H→Rain100L | PSNR: 18.97 -> 29.08 | Helped |
Closest papers by meaning
- Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining (CVPR 2019 · similarity 0.91)
- Deep Joint Rain Detection and Removal From a Single Image (CVPR 2017 · similarity 0.90)
- Incremental Image De-raining via Associative Memory (AAAI 2023 · similarity 0.90)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (AAAI 2025 · similarity 0.90)
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains (ICLR 2024 · similarity 0.88)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · 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.