# Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

arXiv: https://arxiv.org/abs/2011.11559 · HTML: https://mlsanity.com/paper/2011.11559/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 3 of 3)

- [Introducing Vision Transformer for Alzheimer's Disease classification task with 3D input](https://mlsanity.com/paper/2210.01177/) (2022)
- [Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear Detection](https://mlsanity.com/paper/2302.05262/) (2023)
- [Clinical DVH metrics as a loss function for 3D dose prediction in head and neck radiotherapy](https://mlsanity.com/paper/2603.29670/) (2026)

## Abstract (arXiv)

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-the-art segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment. Out of all the compared methods the Instance Normalization achieved the highest result with Dice coefficient = 0.96 which is comparable to our previous results achieved by deeper network with longer training time. We also show that the Instance Normalization implementation used in this experiment is computational time efficient when compared to the network without any normalization method.