# Spectral Batch Normalization: Normalization in the Frequency Domain

arXiv: https://arxiv.org/abs/2306.16999 · HTML: https://mlsanity.com/paper/2306.16999/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Fixup Initialization: Residual Learning Without Normalization](https://mlsanity.com/paper/1901.09321/) (2019)
- [Regularization for Deep Learning: A Taxonomy](https://mlsanity.com/paper/1710.10686/) (2017)
- [Spectral Representations for Convolutional Neural Networks](https://mlsanity.com/paper/1506.03767/) (2015)
- [A Survey of Complex-Valued Neural Networks](https://mlsanity.com/paper/2101.12249/) (2021)
- [Towards Understanding Regularization in Batch Normalization](https://mlsanity.com/paper/1809.00846/) (2018)
- [Regularization of Deep Neural Networks with Spectral Dropout](https://mlsanity.com/paper/1711.08591/) (2017)

## Built on by (most cited first, 2 of 2)

- [Squeeze-and-Remember Block](https://mlsanity.com/paper/2410.00823/) (2024)
- [Fourier Transform Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2510.15138/) (2025)

## Abstract (arXiv)

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce spectral batch normalization (SBN), a novel effective method to improve generalization by normalizing feature maps in the frequency (spectral) domain. The activations of residual networks without batch normalization (BN) tend to explode exponentially in the depth of the network at initialization. This leads to extremely large feature map norms even though the parameters are relatively small. These explosive dynamics can be very detrimental to learning. BN makes weight decay regularization on the scaling factors γ, β approximately equivalent to an additive penalty on the norm of the feature maps, which prevents extremely large feature map norms to a certain degree. However, we show experimentally that, despite the approximate additive penalty of BN, feature maps in deep neural networks (DNNs) tend to explode at the beginning of the network and that feature maps of DNNs contain large values during the whole training. This phenomenon also occurs in a weakened form in non-residual networks. SBN addresses large feature maps by normalizing them in the frequency domain. In our experiments, we empirically show that SBN prevents exploding feature maps at initialization and large feature map values during the training. Moreover, the normalization of feature maps in the frequency domain leads to more uniform distributed frequency components. This discourages the DNNs to rely on single frequency components of feature maps. These, together with other effects of SBN, have a regularizing effect on the training of residual and non-residual networks. We show experimentally that using SBN in addition to standard regularization methods improves the performance of DNNs by a relevant margin, e.g. ResNet50 on ImageNet by 0.71%.