AI Paper Atlas

Research map / Image generation / Super-resolution

Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution

Jiamian Wang, Huan Wang, Yulun Zhang, Yun Fu, Zhiqiang Tao

ICCV 2023 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
use ISS-P instead of ASSL/SRP at pruning ratio 0.99SwinIR-Lightweight · Set5 x4PSNR: 29.15 -> 29.67 vs ASSLImproved
use ISS-P at pruning ratio 0.9, x2 scaleSwinIR-Lightweight · Set5 x2PSNR: 37.66 (ISS-P) vs 37.69 (ASSL)No clear effect
use soft percentage shrinkage (ISS-P) instead of hard thresholding (IHT) (ablation)SwinIR-Lightweight · Set5 x4 (prune 0.9)PSNR: 35.17 -> 35.86Improved
use ISS-P instead of ISS-R (ablation)SwinIR-Lightweight · x4 (prune 0.9)PSNR: 35.37 -> 35.86Improved
use ISS-R instead of IHT (ablation)SwinIR-Lightweight · Set5 prune 0.9PSNR: 37.48 -> 37.38 (x2), 35.17 -> 35.37 (x4)Mixed
use ISS-P on EDSR-L backboneEDSR-L · Urban100 x4 (prune 0.95)PSNR: 24.09 -> 24.43 vs ASSLImproved
use ISS-P on CAT-R backboneCAT-R · Urban100 x4 (prune 0.95)PSNR: 26.09 -> 26.94 vs SRPImproved
use L1-norm static pruning from random init instead of random sparse scratch trainingSwinIR-Lightweight · Urban100 x4 (prune 0.9)PSNR: 25.16 -> 25.16No clear effect
use ISS-P rather than IHT for gradient trainability (ablation)SwinIR-Lightweight · layer-wise gradient norm and variancegradient convergenceImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy