AI Paper Atlas

Research map / Detection and segmentation / CNN features

Attentive Normalization

Xilai Li, Wei Sun, Tianfu Wu

ECCV 2020 · Detection and segmentation › CNN features · approach: Efficient network training and design · 31 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 RSD attention input instead of mean only (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.85 -> 21.59Improved
use RSD instead of concatenated (mean,std) (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.73 -> 21.59Improved
add BN after fc (Choice 2 instead of Choice 1) (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.76 -> 21.59Improved
use hsigmoid instead of softmax (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.72 -> 21.59Improved
use hsigmoid instead of relu (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.89 -> 21.59Improved
use hsigmoid instead of sigmoid (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.96 -> 21.59Improved
use K=(10,10,20,20) instead of (5,5,10,10) (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.92 -> 21.59Improved
use K=(10,10,20,20) instead of larger (20,20,40,40) (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 21.62 -> 21.59No clear effect
replace only the BN after last 3x3 conv instead of all BNs (ablation)ResNet50 AN (w/ BN) · ImageNet-1k valtop-1 error (%): 22.15 -> 21.59Improved
replace BN with ANResNet50 · ImageNet-1k val (vanilla setup)top-1 error (%): 23.01 -> 21.59Improved
replace BN with ANDenseNet121 · ImageNet-1k val (vanilla setup)top-1 error (%): 25.35 -> 22.62Improved
replace BN with ANResNet50 · ImageNet-1k val (state-of-the-art setup)top-1 error (%): 21.08 -> 19.92Improved

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