AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Momentum Batch Normalization for Deep Learning with Small Batch Size

Hongwei Yong, Jianqiang Huang, Deyu Meng, Xiansheng Hua, Lei Zhang

ECCV 2020 · Architectures and efficiency › RNNs and normalization · approach: Batch normalization improvements · 48 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 Batch Renormalization with momentum BNBN with small batch · Mini-ImageNet-100 (batch size 2 per GPU)accuracy (%): 55.47% -> 56.50%Improved
replace BN with MBNResNet50 · ImageNet val (64 GPUs, batch 4 per GPU)accuracy: +2.5%Improved
use inference momentum tau=0.99 (adaptive to batch size) instead of 0.9 (ablation)BN and MBN, batch 2 per GPU · CIFAR100test accuracyImproved
set m0 very small (4) in MBN (ablation)MBN ResNet18 · CIFAR100test accuracyHurt
vary m0 from 16 to 128 (ablation)MBN ResNet18 · CIFAR100test accuracyNo clear effect
replace BN with MBN at batch size 2 per GPUResNet18 · CIFAR10/CIFAR100test accuracyImproved
replace BN with MBN at batch size 8 per GPUResNet18 · CIFAR10/CIFAR100test accuracyNo clear effect
replace BN with MBN on ResNet34, ResNet50, VGG11, VGG16several networks, batch 2 per GPU · CIFAR100test accuracyImproved

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