AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A General Decoupled Learning Framework for Parameterized Image Operators

Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen

TPAMI 2019 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 132 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
train one network on random continuous parameter values instead of one network per value (L0) (ablation)decoupled framework · L0 filterPSNR avg: 36.11 -> 35.25Hurt
train one network on numerous parameter values (WLS) (ablation)decoupled framework · WLS filterSSIM avg: 0.990 -> 0.990No clear effect
joint training on 6/4 operators rather than single operator (ablation)decoupled framework · 10 operatorsPSNR avg: 34.40 -> 32.72Hurt
joint training on all 10 operators rather than single operator (ablation)decoupled framework · 10 operatorsPSNR avg: 34.40 -> 32.18Hurt
use decoupled framework instead of prior baseline for 10 jointly trained operatorsjoint 10 operators · 10 operatorsPSNR avg: 31.02 -> 32.18Improved
use decoupled framework instead of DBLimage operator reproduction · 10 operatorsPSNR avg: 26.92 -> 31.87Improved
place learned parameters deeper in network (norm layer 1 to 19) (ablation)weight learning network · 10 operatorsPSNR avg: 31.21 -> 28.67Hurt
learn conv weights rather than instance norm parameters at layer 19 (ablation)weight learning network · 10 operatorsPSNR avg: 28.67 -> 30.85Improved
learn norm in all layers rather than first layer only (ablation)weight learning network · 10 operatorsPSNR avg: 31.21 -> 31.62No clear effect
learn all conv layers instead of all norm layers (ablation)weight learning network · 10 operatorsPSNR avg: 31.62 -> 31.63No clear effect
add weight learning network to base network (single parameter) (ablation)base network · WLS filterPSNR avg: 40.54 -> 41.52Improved
add a second FC layer to weight learning network (ablation)weight learning network · WLS filterPSNR avg: 40.91 -> 39.67No clear effect

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