Research map / Image generation / Image restoration
Dreaming To Prune Image Deraining Networks
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 |
|---|---|---|---|
| Use adaptive pruning (AP) instead of fixed ℓ1 pruning (ablation) | HINet · Five deraining validation datasets | PSNR: 5.01 dB | Helped |
| Add data-free knowledge distillation using dreamed inputs (ablation) | Adaptively pruned HINet · Five deraining validation datasets | PSNR: 0.9 dB | Helped |
| Add batch diversity loss Lorth to dreamed inputs (ablation) | HINet dreaming-for-distillation framework · Rain100H | PSNR: 1.3 dB | Helped |
| Add batch diversity loss Lorth to dreamed inputs (ablation) | HINet dreaming-for-distillation framework · Test100 | PSNR: 1.8 dB | Helped |
| Prune HINet with adaptive pruning and dreamed-data distillation rather than the original model | HINet · Rain13k average | PSNR: 33.03 -> 32.67 | Hurt |
Closest papers by meaning
- Progressive Image Deraining Networks: A Better and Simpler Baseline (CVPR 2019 · similarity 0.90)
- Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures (CVPR 2023 · similarity 0.87)
- Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework (ICLR 2025 · similarity 0.86)
- Rethinking Multi-Scale Representations in Deep Deraining Transformer (AAAI 2024 · similarity 0.86)
- Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold (AAAI 2024 · similarity 0.86)
- UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer (AAAI 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.