# Dynamic Normalization

Source: [Dynamic Normalization](<https://www.sota2.com/research/paper/68fa69181e209131cea202f3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:53:51.580Z

Authors: Chuan Liu, Yi Gao, Jiancheng Lv

Published: 2021-01-15T11:41:41.000Z

## Abstract

Batch Normalization has become one of the essential components in CNN. It allows the network to use a higher learning rate and speed up training. And the network doesn't need to be initialized carefully. However, in our work, we find that a simple extension of BN can increase the performance of the network. First, we extend BN to adaptively generate scale and shift parameters for each mini-batch data, called DN-C (Batch-shared and Channel-wise). We use the statistical characteristics of mini-batch data ($E\[X\], Std\[X\]\\in\\mathbb{R}^{c}$) as the input of SC module. Then we extend BN to adaptively generate scale and shift parameters for each channel of each sample, called DN-B (Batch and Channel-wise). Our experiments show that DN-C model can't train normally, but DN-B model has very good robustness. In classification task, DN-B can improve the accuracy of the MobileNetV2 on ImageNet-100 more than 2% with only 0.6% additional Mult-Adds. In detection task, DN-B can improve the accuracy of the SSDLite on MS-COCO nearly 4% mAP with the same settings. Compared with BN, DN-B has stable performance when using higher learning rate or smaller batch size.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2101.06073>)

[PDF](<https://arxiv.org/pdf/2101.06073.pdf>)
