# Enhancing Neural Network Representations with Prior Knowledge-Based Normalization

arXiv: https://arxiv.org/abs/2403.16798 · HTML: https://mlsanity.com/paper/2403.16798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models](https://mlsanity.com/paper/1702.03275/) (2017)
- [AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation](https://mlsanity.com/paper/2106.04732/) (2021)
- [Evolving Normalization-Activation Layers](https://mlsanity.com/paper/2004.02967/) (2020)
- [Switchable Normalization for Learning-to-Normalize Deep Representation](https://mlsanity.com/paper/1907.10473/) (2019)
- [Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes](https://mlsanity.com/paper/1611.04520/) (2016)
- [Training Faster by Separating Modes of Variation in Batch-normalized Models](https://mlsanity.com/paper/1806.02892/) (2018)
- [MuVieCAST: Multi-View Consistent Artistic Style Transfer](https://mlsanity.com/paper/2312.05046/) (2023)

## Abstract (arXiv)

Deep learning models face persistent challenges in training, particularly due to internal covariate shift and label shift. While single-mode normalization methods like Batch Normalization partially address these issues, they are constrained by batch size dependencies and limiting distributional assumptions. Multi-mode normalization techniques mitigate these limitations but struggle with computational demands when handling diverse Gaussian distributions. In this paper, we introduce a new approach to multi-mode normalization that leverages prior knowledge to improve neural network representations. Our method organizes data into predefined structures, or "contexts", prior to training and normalizes based on these contexts, with two variants: Context Normalization (CN) and Context Normalization - Extended (CN-X). When contexts are unavailable, we introduce Adaptive Context Normalization (ACN), which dynamically builds contexts in the latent space during training. Across tasks in image classification, domain adaptation, and image generation, our methods demonstrate superior convergence and performance.