Research map / Architectures and efficiency / CNN design
Second-Order Attention Network for Single Image Super-Resolution
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 SAN instead of RCAN | SAN · Set5, BI ×4 | PSNR: 32.62 -> 32.64 | Helped |
| Use SAN instead of RCAN | SAN · Set14, BI ×4 | PSNR: 28.86 -> 28.92 | Helped |
| Use SAN instead of RCAN | SAN · Urban100, BI ×4 | PSNR: 26.82 -> 26.79 | Hurt |
| Use SAN instead of RCAN | SAN · Manga109, BI ×4 | PSNR: 31.21 -> 31.18 | Hurt |
| Use SAN instead of RCAN | SAN · BSD100, BI ×4 | PSNR: 27.76 -> 27.78 | Helped |
| Add RL-NL before SSRG (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.04 | Helped |
| Add RL-NL after SSRG (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.06 | Helped |
| Add share-source skip connection (SSC) (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.07 | Helped |
| Add first-order channel attention (FOCA) (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.12 | Helped |
| Add second-order channel attention (SOCA) (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.16 | Helped |
| Combine RL-NL before and after SSRG, SSC, and SOCA (ablation) | SAN · Set5, BI ×4 | PSNR: 32.00 -> 32.20 | Helped |
| Use SAN instead of RCAN | SAN · Set5, BD ×3 | PSNR: 34.70 -> 34.75 | Helped |
Closest papers by meaning
- Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining (CVPR 2020 · similarity 0.90)
- CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution (CVPR 2023 · similarity 0.89)
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR 2016 · similarity 0.88)
- FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks (AAAI 2023 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.87)
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.