# Entropic Out-of-Distribution Detection

arXiv: https://arxiv.org/abs/1908.05569 · HTML: https://mlsanity.com/paper/1908.05569/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 21 of 21)

- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [Learning on Graphs with Out-of-Distribution Nodes](https://mlsanity.com/paper/2308.06714/) (2023)
- [iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection](https://mlsanity.com/paper/2201.02331/) (2022)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models](https://mlsanity.com/paper/2404.12667/) (2024)
- [Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss](https://mlsanity.com/paper/2105.14399/) (2021)
- [Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes](https://mlsanity.com/paper/2112.10558/) (2021)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection](https://mlsanity.com/paper/2212.02081/) (2022)
- [Morse Neural Networks for Uncertainty Quantification](https://mlsanity.com/paper/2307.00667/) (2023)
- [GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence](https://mlsanity.com/paper/2307.09810/) (2023)
- [Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios](https://mlsanity.com/paper/2504.13478/) (2025)
- [Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating](https://mlsanity.com/paper/2205.05874/) (2022)
- [SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier](https://mlsanity.com/paper/2206.13923/) (2022)
- [Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods](https://mlsanity.com/paper/2402.12664/) (2024)
- [Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving](https://mlsanity.com/paper/2501.08083/) (2025)
- [Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs](https://mlsanity.com/paper/2509.04655/) (2025)
- [Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation](https://mlsanity.com/paper/2307.09929/) (2023)
- [When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty](https://mlsanity.com/paper/2505.13989/) (2025)
- [Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking](https://mlsanity.com/paper/2512.19725/) (2025)
- [Towards Robust Deep Learning using Entropic Losses](https://mlsanity.com/paper/2208.03566/) (2022)

## Abstract (arXiv)

Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., classification accuracy drop, slower energy-inefficient inferences). We argue that these issues are a consequence of the SoftMax loss anisotropy and disagreement with the maximum entropy principle. Thus, we propose the IsoMax loss and the entropic score. The seamless drop-in replacement of the SoftMax loss by IsoMax loss requires neither additional data collection nor hyperparameter validation. The trained models do not exhibit classification accuracy drop and produce fast energy-efficient inferences. Moreover, our experiments show that training neural networks with IsoMax loss significantly improves their OOD detection performance. The IsoMax loss exhibits state-of-the-art performance under the mentioned conditions (fast energy-efficient inference, no classification accuracy drop, no collection of outlier data, and no hyperparameter validation), which we call the seamless OOD detection task. In future work, current OOD detection methods may replace the SoftMax loss with the IsoMax loss to improve their performance on the commonly studied non-seamless OOD detection problem.