# Understanding normalization in contrastive representation learning and out-of-distribution detection

arXiv: https://arxiv.org/abs/2312.15288 · HTML: https://mlsanity.com/paper/2312.15288/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 23 Dec 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2010.05903/) (2020)
- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization](https://mlsanity.com/paper/2109.15222/) (2021)
- [Deep Nearest Neighbor Anomaly Detection](https://mlsanity.com/paper/2002.10445/) (2020)
- [Detecting semantic anomalies](https://mlsanity.com/paper/1908.04388/) (2019)
- [Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images](https://mlsanity.com/paper/2205.11474/) (2022)

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

- [Mahalanobis++: Improving OOD Detection via Feature Normalization](https://mlsanity.com/paper/2505.18032/) (2025)
- [A Geometry-Based View of Mahalanobis OOD Detection](https://mlsanity.com/paper/2510.15202/) (2025)

## Abstract (arXiv)

Contrastive representation learning has emerged as an outstanding approach for anomaly detection. In this work, we explore the ℓ2-norm of contrastive features and its applications in out-of-distribution detection. We propose a simple method based on contrastive learning, which incorporates out-of-distribution data by discriminating against normal samples in the contrastive layer space. Our approach can be applied flexibly as an outlier exposure (OE) approach, where the out-of-distribution data is a huge collective of random images, or as a fully self-supervised learning approach, where the out-of-distribution data is self-generated by applying distribution-shifting transformations. The ability to incorporate additional out-of-distribution samples enables a feasible solution for datasets where AD methods based on contrastive learning generally underperform, such as aerial images or microscopy images. Furthermore, the high-quality features learned through contrastive learning consistently enhance performance in OE scenarios, even when the available out-of-distribution dataset is not diverse enough. Our extensive experiments demonstrate the superiority of our proposed method under various scenarios, including unimodal and multimodal settings, with various image datasets.