AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Centered Weight Normalization in Accelerating Training of Deep Neural Networks

Lei Huang, Xianglong Liu, Yang Liu, Bo Lang, Dacheng Tao

ICCV 2017 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 71 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
add weight centering (CWN) to weight normalization (WN) (ablation)WN · Yale-B (MLP)test error: 4.68 -> 4.20Improved
add weight centering (CWN) to weight normalization (WN) (ablation)WN · SVHN permutation-invariant (MLP)test error: 17.12 -> 16.16Improved
CWN vs plain with He-Initplain · SVHN permutation-invariant (MLP, He-Init)test error: 18.35 -> 16.71Improved
CWN vs plain with Xavier-Initplain · Yale-B (MLP, Xavier-Init)test error: 6.47 -> 3.84Improved
add WN to plain networkplain · CIFAR-10 (ResNet-56)test error: 7.34 -> 7.58Hurt
add CWN to plain ResNet-56plain · CIFAR-100 (ResNet-56)test error: 29.38 -> 29.23No clear effect
add WN to plain VGG-Aplain · CIFAR-10 (VGG-A)test error: 14.33% -> 15.89%Hurt
add CWN to plain VGG-Aplain · CIFAR-10 (VGG-A)test error: 14.33% -> 13.06%Improved
add CWN to plain GoogLeNetplain · CIFAR-100 (GoogLeNet)test error: 25.52% -> 24.45%Improved
add CWN to plain GoogLeNetplain · ImageNet-2012 val (top-1)top-1 error: 30.78 -> 26.1Improved
add CWN to plain GoogLeNetplain · ImageNet-2012 val (top-5)top-5 error: 11.14 -> 8.35Improved
add centering (CWN) on top of batch normalization (CWN+BN vs WN+BN, NNN+BN) (ablation)BN · SVHN permutation-invariant (MLP)speed and test errorImproved

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