# Instance-Level Meta Normalization

arXiv: https://arxiv.org/abs/1904.03516 · HTML: https://mlsanity.com/paper/1904.03516/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Adversarially Adaptive Normalization for Single Domain Generalization](https://mlsanity.com/paper/2106.01899/) (2021)
- [Source-Free Domain Adaptation for Real-world Image Dehazing](https://mlsanity.com/paper/2207.06644/) (2022)
- [Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity](https://mlsanity.com/paper/2102.11382/) (2021)
- [MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation](https://mlsanity.com/paper/2109.09734/) (2021)
- [Revisiting Batch Norm Initialization](https://mlsanity.com/paper/2110.13989/) (2021)
- [SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction](https://mlsanity.com/paper/2210.10725/) (2022)
- [KL Regularized Normalization Framework for Low Resource Tasks](https://mlsanity.com/paper/2212.11275/) (2022)

## Abstract (arXiv)

This paper presents a normalization mechanism called Instance-Level Meta Normalization (ILM~Norm) to address a learning-to-normalize problem. ILM~Norm learns to predict the normalization parameters via both the feature feed-forward and the gradient back-propagation paths. ILM~Norm provides a meta normalization mechanism and has several good properties. It can be easily plugged into existing instance-level normalization schemes such as Instance Normalization, Layer Normalization, or Group Normalization. ILM~Norm normalizes each instance individually and therefore maintains high performance even when small mini-batch is used. The experimental results show that ILM~Norm well adapts to different network architectures and tasks, and it consistently improves the performance of the original models. The code is available at url{https://github.com/Gasoonjia/ILM-Norm.