OOD Detection

OOD: Out-of-Distribution

Ask about this topic

Overview

OOD detection asks whether an input falls outside the data a model learned from, helping prevent confident errors when conditions or classes change. Common approaches score softmax or energy outputs, compare feature distances with Mahalanobis or k-nearest-neighbor methods, model density with generative models, or learn boundaries using synthetic outliers; pretrained vision-language models and test-time adaptation are increasingly used as well. Methods are tested on near- and far-OOD image benchmarks such as CIFAR and ImageNet, and in settings including medical imaging, language models, graphs, and autonomous driving. A central challenge is that strong benchmark scores may not transfer across domains: subtle shifts can evade detectors, while rejecting unknowns can also discard valid in-distribution inputs or fail to predict downstream harm.

Latest papers

CardsList

225 papers19 papers in the last four weeks, up 12% on the four weeks before. 0.1% of all new papers.

  1. Beyond a Single Signal: SPECTREG2, A Unified MultiExpert Anomaly Detector for Unknown Unknowns

    Mar 22, 2026Rahul D RayAnomaly DetectionOOD Detection

    Department of Electronics and Electrical Engineering, BITS Pilani, Hyderabad Campus

  2. T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World

    Mar 19, 2026Aditi Naiknaware, Salimeh SekehVLM RobustnessDomain Generalization

    San Diego State University

  3. LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs

    Mar 19, 2026Xiaoxu Ma, Dong Li, Minglai Shao +2OOD DetectionText-Attributed Graph Learning

    School of New Media and Communication, Tianjin University, China · Department of Computer Science, Baylor University, USA · Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, China +1

  4. CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring

    Mar 18, 2026Jin Mo Yang, Hyung-Sin Kim, Saewoong BahkOOD Detection

    Seoul National University, Seoul, South Korea

  5. Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning

    Mar 17, 2026Sadia Ilyas, Annika Mütze, Klaus Friedrichs +2Object DetectionOOD Detection

    University of Wuppertal · Aptiv Services Deutschland GmbH · University of Osnabrück, Germany

  6. Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments

    Mar 16, 2026Aaditya Khanal, Junxiu ZhouSkeleton-Based Action RecognitionSelective Prediction

    School of Computing and Analytics, Northern Kentucky University, Highland Heights, KY 41099, USA

  7. Tracking the Discriminative Axis: Dual Prototypes for Test-Time OOD Detection Under Covariate Shift

    Mar 16, 2026Wooseok Lee, Jin Mo Yang, Saewoong Bahk +1OOD DetectionCovariate Shift

    Seoul National University, Seoul, Korea

  8. Latent Dynamics-Aware OOD Monitoring for Trajectory Prediction with Provable Guarantees

    Mar 15, 2026Tongfei Guo, Lili SuOOD DetectionChange-Point Detection

    Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA.

  9. Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models

    Mar 11, 2026Hong Yang, Devroop Kar, Qi Yu +2OOD DetectionDistribution Shift

    Rochester Institute of Technology, Rochester, NY 14623, USA

  10. Geometrically Constrained Outlier Synthesis

    Mar 9, 2026Daniil Karzanov, Marcin DetynieckiOOD DetectionSynthetic Anomaly Generation

    AXA AI Research · EPFL, Lausanne, Switzerland · TRAIL, Sorbonne Université, Paris, France +1

  11. Local-Global Prompt Learning via Sparse Optimal Transport

    Mar 9, 2026Deniz Kizaroğlu, Ülku Tuncer Küçüktas, Emre Çakmakyurdu +1VLM AdaptationVisual Prompt Learning

    Graduate School of Informatics, Middle East Technical University, Ankara, Turkey · Department of Electrical and Electronics Engineering, Gazi University, Ankara, Turkey

  12. ALOOD: Exploiting Language Representations for LiDAR-based Out-of-Distribution Object Detection

    Mar 9, 2026Michael Kösel, Marcel Schreiber, Michael Ulrich +2OOD DetectionLidar-Based 3D Object Detection

    Institute of Measurement, Control, and Microtechnology, Ulm University, Germany · Robert Bosch GmbH, Corporate Research, 71272 Renningen, Germany

  13. A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification

    Mar 8, 2026Furkan Genç, Onat Özdemir, Emre AkbaşOOD DetectionImage Classification

    Dept. of Electrical and Electronics Engineering, Bilkent University · Dept. of Computer Engineering, Middle East Technical University

  14. Shaping Parameter Contribution Patterns for Out-of-Distribution Detection

    Mar 7, 2026Haonan Xu, Yang YangOOD DetectionDistribution Shift Robustness

    Nanjing University of Science and Technology

  15. PromptGate Client Adaptive Vision Language Gating for Open Set Federated Active Learning

    Mar 7, 2026Adea Nesturi, David Dueñas Gaviria, Jiajun Zeng +1Active LearningFederated Learning

    University of Bonn, University Hospital Bonn, Clinic for Diagnostic and Interventional Radiology, 53127 Bonn, Germany

  16. How to Achieve Prototypical Birth and Death for OOD Detection?

    Mar 6, 2026Ningkang Peng, Qianfeng Yu, Xiaoqian Peng +7OOD DetectionPrototype-Based Classification

    School of Computer and Electronic Information, Nanjing Normal University · School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen +1

  17. The Challenge of Out-Of-Distribution Detection in Motor Imagery BCIs

    Mar 4, 2026Merlijn Quincent Mulder, Matias Valdenegro-Toro, Andreea Ioana Sburlea +1OOD DetectionBrain-Computer Interfaces

    Department of Artificial Intelligence, University of Groningen 9747 AG Groningen, The Netherlands

  18. From Misclassifications to Outliers: Joint Reliability Assessment in Classification

    Mar 4, 2026Yang Li, Youyang Sha, Yinzhi Wang +4Confidence EstimationClassification

    Intellindust AI Lab, Shenzhen, 518000, China. · Samsung AI Center, Cambridge, CB1 2GA, United Kingdom.

  19. Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs

    Mar 3, 2026Zhikang Xu, Qianqian Xu, Zitai Wang +4OOD DetectionVision-Language Models

    Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences +2

  20. Adaptive Confidence Regularization for Multimodal Failure Detection

    Mar 2, 2026Moru Liu, Hao Dong, Olga Fink +1Multimodal RobustnessMultimodal Anomaly Detection

    Technical University of Munich · ETH Zürich · EPFL +1

  21. Vision-Language Feature Alignment for Road Anomaly Segmentation

    Mar 1, 2026Zhuolin He, Jiacheng Tang, Jian Pu +1Image SegmentationAutonomous Driving Perception

    School of Computer Science, Fudan University, Shanghai 200433, China · Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, 200433, China

  22. Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection

    Feb 28, 2026Li Sun, Lanxu Yang, Jiayu Tian +6OOD DetectionSynthetic Anomaly Generation

    North China Electric Power University · Beijing University of Posts and Telecommunications · Tsinghua University +4

  23. Deep Learning-Based Meat Freshness Detection with Segmentation and OOD-Aware Classification

    Feb 27, 2026Hutama Arif Bramantyo, Mukarram Ali Faridi, Rui Chen +2ClassificationImage Classification

    Electrical & Computer Engineering Department, College of Engineering, Auburn University, Auburn, AL 36849 USA · Department of Agricultural and Environmental Sciences, College of Agriculture, Environment & Nutrition Sciences, Tuskegee University, Tuskegee, AL 36088 USA

  24. ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models

    Feb 27, 2026Wei Luo, Yangfan Ou, Jin Deng +4VLM RobustnessTest-Time Adaptation

    South China Agricultural University · Pazhou Laboratory · South China University of Technology +1

  25. Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory

    Feb 25, 2026Davide EttoriLLM CompressionRepresentation Geometry in Language Models

  26. ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding

    Feb 24, 2026Ziyi Liang, Hamed Poursiami, Zhishun Yang +5Hyperdimensional ComputingNeuromorphic Computing

    Department of Statistics, UC Irvine, Irvine, CA, USA · Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA · Center for the Neurobiology of Learning and Memory, UC Irvine, Irvine, CA, USA +2

  27. The Invisible Gorilla Effect in Out-of-distribution Detection

    Feb 23, 2026Harry Anthony, Ziyun Liang, Hermione Warr +1OOD Detection

    Department of Engineering Science, University of Oxford, Oxford, UK

  28. Self-Aware Object Detection via Degradation Manifolds

    Feb 20, 2026Stefan Becker, Simon Weiss, Wolfgang Hübner +1Object DetectionOOD Detection

    Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB Gutleuthausstraße 1, 76275 Ettlingen

  29. From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection

    Feb 19, 2026Luzhi Wang, Xuanshuo Fu, He Zhang +3Graph Prompt LearningOOD Detection

    College of Artificial Intelligence, Dalian Maritime University · Computer Vision Center, Universitat Aut`onoma de Barcelona · School of Computing Technologies, RMIT University +1

  30. World Model Failure Classification and Anomaly Detection for Autonomous Inspection

    Feb 18, 2026Michelle Ho, Muhammad Fadhil Ginting, Isaac R. Ward +4Robot Failure DetectionRobotic Anomaly Detection

    Stanford University, Stanford, CA 94305 USA · Field AI, Mission Viejo, CA 92691 USA