Research map / Architectures and efficiency / CNN design
Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution
Read the paperCheck 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 FDIWN instead of the strongest listed baseline | SISR models · Set5 ×3 | PSNR: 34.42 -> 34.52 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · Set14 ×3 | PSNR: 30.35 -> 30.42 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · BSDS100 ×3 | PSNR: 29.13 -> 29.14 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · Urban100 ×3 | PSNR: 28.26 -> 28.36 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · Set5 ×4 | PSNR: 32.24 -> 32.23 | Hurt |
| Use FDIWN instead of the strongest listed baseline | SISR models · Set14 ×4 | PSNR: 28.65 -> 28.66 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · BSDS100 ×4 | PSNR: 27.61 -> 27.62 | Helped |
| Use FDIWN instead of the strongest listed baseline | SISR models · Urban100 ×4 | PSNR: 26.14 -> 26.28 | Helped |
| Add WRDC to the Baseline1 design without SCF (ablation) | FDIWN · Set5 | PSNR: 37.52 -> 37.59 | Helped |
| Add SCF to the Baseline1 design without WRDC (ablation) | FDIWN · Set5 | PSNR: 37.52 -> 37.58 | Helped |
| Add both WRDC and SCF to Baseline1 (ablation) | FDIWN · Set5 | PSNR: 37.52 -> 37.64 | Helped |
| Use 120 rather than 48 channels in WIRW and WCRW (ablation) | FDIWN · Set5 | PSNR: 37.64 -> 37.72 | Helped |
Closest papers by meaning
- Fast and Accurate Single Image Super-Resolution via Information Distillation Network (CVPR 2018 · similarity 0.87)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.85)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.85)
- OSFFNet: Omni-Stage Feature Fusion Network for Lightweight Image Super-Resolution (AAAI 2024 · similarity 0.85)
- Lightweight Image Super-Resolution via Flexible Meta Pruning (ICML 2024 · similarity 0.85)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.84)
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.