AI Paper Atlas

Research map / Image generation / Image restoration

Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization

Lanning Zhang, Ying Zhou, Fei Gao, Ziyun Li, Maoying Qiao, Jinlan Xu, Nannan Wang

ICCV 2025 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 1 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
replace BN with channel-wise Q-Norm on CODaN NightResNet18 · CODaN NightTop1 accuracy: 0.308 -> 0.292Hurt
use spatial-wise Q-Norm instead of BNResNet18 · CODaN NightTop1 accuracy: 0.308 -> 0.356Improved
add Q-Norm to detectorRT-DETR · HazyDetAvg mAP50: 45.40 -> 48.00Improved
add Q-Norm to detectorYOLOv11 · HazyDetAvg mAP50: 63.00 -> 63.70Improved
Q-Norm versus data augmentation on blurred VOCYOLOv11 · VOC blur (avg)mAP50: 63.30 -> 64.00Improved
Q-Norm versus data augmentation on blurred PASCAL-Context semsegMTMamba · PASCAL-Context semseg (avg)mIoU: 76.40 -> 76.19 (ch), 76.46 (ch-sp)No clear effect
Q-Norm versus data augmentation on normal estimationMTMamba · PASCAL-Context normals (avg)mErr (lower better): 14.99 -> 15.16Hurt
Q-Norm versus data augmentation on image translationMATEBIT · MetfaceFID: 39.56 -> 34.61Improved
use CONTRIQUE instead of BRISQUE as quality model (ablation)Q-Norm · CODaN Nightaccuracy %: 30.80 -> 35.60Improved
use any IQA model for Q-Norm on HazyDet (ablation)Q-Norm · HazyDetmAP50 %: 45.40 -> 47.60 (BRISQUE), 48.00 (CNN, CONTRIQUE)Improved
apply channel then spatial Q-Norm jointly instead of spatial then channel (ablation)YOLOv11 · VOCavg mAP50: 59.85 -> 63.60Improved
insert Q-Norm at the front of the backbone rather than later layers (ablation)YOLOv11, MTMamba · VOC / PASCAL-ContextmAP / mIoUImproved

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