# Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

arXiv: https://arxiv.org/abs/2206.09880 · HTML: https://mlsanity.com/paper/2206.09880/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 20 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder](https://mlsanity.com/paper/2003.02977/) (2020)
- [Adversarial Robustness on In- and Out-Distribution Improves Explainability](https://mlsanity.com/paper/2003.09461/) (2020)
- [Towards neural networks that provably know when they don't know](https://mlsanity.com/paper/1909.12180/) (2019)
- [TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks](https://mlsanity.com/paper/1604.06318/) (2016)
- [Hybrid Models with Deep and Invertible Features](https://mlsanity.com/paper/1902.02767/) (2019)

## Built on by (most cited first, 23 of 23)

- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation](https://mlsanity.com/paper/2306.00826/) (2023)
- [Energy-based Out-of-Distribution Detection for Graph Neural Networks](https://mlsanity.com/paper/2302.02914/) (2023)
- [Out-of-distribution Detection with Implicit Outlier Transformation](https://mlsanity.com/paper/2303.05033/) (2023)
- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [Learning to Augment Distributions for Out-of-Distribution Detection](https://mlsanity.com/paper/2311.01796/) (2023)
- [DOS: Diverse Outlier Sampling for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.02031/) (2023)
- [Plugin estimators for selective classification with out-of-distribution detection](https://mlsanity.com/paper/2301.12386/) (2023)
- [Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection](https://mlsanity.com/paper/2303.01201/) (2023)
- [Revisiting Confidence Estimation: Towards Reliable Failure Prediction](https://mlsanity.com/paper/2403.02886/) (2024)
- [Calibrated Out-of-Distribution Detection with a Generic Representation](https://mlsanity.com/paper/2303.13148/) (2023)
- [Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection](https://mlsanity.com/paper/2510.05782/) (2025)
- [Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution](https://mlsanity.com/paper/2407.16430/) (2024)
- [What If the Input is Expanded in OOD Detection?](https://mlsanity.com/paper/2410.18472/) (2024)
- [Rule-based Out-Of-Distribution Detection](https://mlsanity.com/paper/2303.01860/) (2023)
- [Redesigning Out-of-Distribution Detection on 3D Medical Images](https://mlsanity.com/paper/2308.07324/) (2023)
- [Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection](https://mlsanity.com/paper/2508.00587/) (2025)
- [Improving Out-of-Distribution Detection by Combining Existing Post-hoc Methods](https://mlsanity.com/paper/2407.07135/) (2024)
- [A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers](https://mlsanity.com/paper/2308.04137/) (2023)
- [An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivity](https://mlsanity.com/paper/2509.13375/) (2025)
- [BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse](https://mlsanity.com/paper/2511.13539/) (2025)
- [Incremental Object-Based Novelty Detection with Feedback Loop](https://mlsanity.com/paper/2311.09004/) (2023)
- [Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detection](https://mlsanity.com/paper/2609.20299/) (2026)

## Abstract (arXiv)

It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution task. Many out-of-distribution detection methods have been suggested in recent years. The goal of this paper is to recognize common objectives as well as to identify the implicit scoring functions of different OOD detection methods. We focus on the sub-class of methods that use surrogate OOD data during training in order to learn an OOD detection score that generalizes to new unseen out-distributions at test time. We show that binary discrimination between in- and (different) out-distributions is equivalent to several distinct formulations of the OOD detection problem. When trained in a shared fashion with a standard classifier, this binary discriminator reaches an OOD detection performance similar to that of Outlier Exposure. Moreover, we show that the confidence loss which is used by Outlier Exposure has an implicit scoring function which differs in a non-trivial fashion from the theoretically optimal scoring function in the case where training and test out-distribution are the same, which again is similar to the one used when training an Energy-Based OOD detector or when adding a background class. In practice, when trained in exactly the same way, all these methods perform similarly.