Research map / Image generation / Super-resolution
Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks
Cheeun Hong, Kyoung Mu Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 weight clipping correction (ablation) | ODM (2-bit EDSR) · Set5 | PSNR: 29.94 -> 31.12 | Improved |
| naively add mismatch regularization to reconstruction loss (ablation) | ODM (2-bit EDSR) · Set5 | PSNR: 31.12 -> 30.99 | Hurt |
| weigh mismatch regularization gradient by cosine similarity with reconstruction gradient (cooperative) (ablation) | ODM (2-bit EDSR) · Set5 | PSNR: 30.99 -> 31.50 | Improved |
| add cooperative mismatch regularization without weight clipping correction (ablation) | ODM (2-bit EDSR) · Set5 | PSNR: 29.94 -> 30.34 | Improved |
| ODM in place of dynamic quantization modules (DAQ, DDTB) | EDSR 2-bit · Set5 | PSNR: 31.01 -> 31.50 | Improved |
| ODM on RDN 2-bit | RDN · Set5 | PSNR: 30.71 -> 31.37 | Improved |
| ODM on SwinIR 2-bit versus QuantSR (300K iterations) | SwinIR · Set5 | PSNR: 31.53 -> 31.67 | Improved |
| ODM versus DAQ computation overhead | EDSR 2-bit · complexity | BitOPs: 215.6T -> 215.1T | Improved |
Closest papers by meaning
- Outlier-Aware Post-Training Quantization for Image Super-Resolution (ICCV 2025 · similarity 0.91)
- AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution (CVPR 2024 · similarity 0.87)
- 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution (NeurIPS 2024 · similarity 0.87)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.87)
- Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues (AAAI 2025 · similarity 0.86)
- PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution (CVPR 2025 · 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.
