EOOD: Entropy-based Out-of-distribution Detection

  • Guide Yang
  • , Chao Hou
  • , Weilong Peng
  • , Xiang Fang
  • , Yongwei Nie
  • , Peican Zhu
  • , Keke Tang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods.

Original languageEnglish
Title of host publicationInternational Joint Conference on Neural Networks, IJCNN 2025 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331510428
DOIs
StatePublished - 2025
Event2025 International Joint Conference on Neural Networks, IJCNN 2025 - Rome, Italy
Duration: 30 Jun 20255 Jul 2025

Publication series

NameProceedings of the International Joint Conference on Neural Networks
ISSN (Print)2161-4393
ISSN (Electronic)2161-4407

Conference

Conference2025 International Joint Conference on Neural Networks, IJCNN 2025
Country/TerritoryItaly
CityRome
Period30/06/255/07/25

Keywords

  • Deep Neural Networks
  • Entropy
  • Out-of-distribution Detection

Fingerprint

Dive into the research topics of 'EOOD: Entropy-based Out-of-distribution Detection'. Together they form a unique fingerprint.

Cite this