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. Does System Size Matter in Uncertainty Quantification for Machine Learning Interatomic Potentials?

    Oct 29, 2026Chayaphol Lortaraprasert, Nontawat Charoenphakdee, Wenwen Li +2Uncertainty QuantificationMachine Learning Interatomic Potentials

    Massachusetts Institute of Technology · Preferred Networks

  2. Modular Bayesian Foundation Models: Bayesian time series encoders for OOD detection, routing and forecasting

    Oct 28, 2026Mame Diarra Toure, Quang Hung Pham, Mohamed Ryad Zemouri +3Time-Series Foundation ModelsModular Neural Networks

    Department of Mathematics and Statistics McGill University · Hydro-Quebec

  3. Enhancing Clinical Classifier Robustness with Deep Representation Learning Based OOD Detection on DNA Methylation Data

    Oct 26, 2026Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar +1OOD DetectionRobust Classification

    St. Jude Children’s Research Hospital, Memphis,TN 38105 USA

  4. Evaluating Bayesian deep learning for robust biomedical time-series classification under distribution shift: A sleep scoring case study

    Oct 26, 2026Mads Birch Sørensen, Ulrike Richter, Francois Gastambide +1Distribution Shift RobustnessTime Series Classification

    Technical University of Denmark, Denmark · H. Lundbeck A/S, Denmark

  5. Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection

    Oct 24, 2026Akito Shinohara, Hiroaki AizawaOOD DetectionWeight-Space Learning

    Graduate School of Advanced Science and Engineering, Hiroshima University, Japan

  6. Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection

    Oct 23, 2026Donghwan Kim, Youngwoong Jin, Hyunsoo YoonOOD Detection

    Department of Industrial Engineering, Yonsei University, Seoul, South Korea · Department of Intelligent Data and Optimization, Yonsei University, Seoul, South Korea

  7. LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels

    Oct 22, 2026Jihoon Hong, Alireza Kheirandish, Rohan Sanda +1Superpixel SegmentationAnomaly Detection

    Georgia Institute of Technology, Atlanta, GA, USA · Stanford University, Stanford, CA, USA · Cohere

  8. Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset

    Oct 22, 2026Lohith Srikanth Pentapalli, Josette Riep, Justin Ouwerkerk +1Anomaly DetectionInterpretable Anomaly Detection

    University of Cincinnati

  9. A Theoretical Analysis of Environment-Aware Out-of-Distribution Detection for Vision-Language Models

    Oct 19, 2026Salimeh Sekeh, Mary WisellOOD DetectionContinual Learning for VLMs

    San Diego State University, San Diego, CA, USA

  10. TriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform Consistency

    Oct 19, 2026Ege Gursoy, Nicolas MansardOOD Detection

    LAAS-CNRS · ANITI

  11. Out-of-Distribution Detection in Continual Learning

    Oct 19, 2026Nimeshika Udayangani, Flora D. Salim, Christopher Leckie +1OOD DetectionContinual Learning

    School of Computing and Information Systems, The University of Melbourne, Australia · School of Computer Science Engineering, University of New South Wales, Australia

  12. Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD

    Oct 16, 2026Yibo Zhou, Yirong XiangCounterfactual Evaluation of VLMsCompositional Reasoning in VLMs

    Beihang University · Air Force Medical Center

  13. Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation

    Oct 12, 2026Vaibhav Prajapati, Pushp GargOpen-Set RecognitionOOD Detection

    University of Technology Nuremberg, Nuremberg, Germany · Indian Institute of Information Sri City, Chittoor, India

  14. Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery

    Oct 10, 2026Tianle Liu, Fan Lyu, Tingliang Feng +6Continual Test-Time AdaptationOOD Detection

    School of Electronics and Information Engineering, Suzhou University of Science and Technology · Computer Vision Center, Universitat Autònoma de Barcelona · College of Computer Science, Northwest University +4

  15. Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances

    Oct 9, 2026Konstantin Ievtushenko, Ralf Lämmel, Jan JürjensSoftware Vulnerability DetectionDistribution Shift

    University of Koblenz, Germany · Fraunhofer ISST, Germany

  16. Human Pose Estimation by Probabilistic Mixtures of Gaussian and Uniform Distributions

    Oct 8, 2026Santiago Reina Alguacil, Ezequiel López RubioHuman Pose EstimationGaussian Mixture Models

    Department of Computer Languages and Computer Science, University of Málaga, 29071 Málaga, Spain · Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina – IBIMA Plataforma BIONAND, 29590 Málaga, Spain · ITIS Software, University of Málaga, 29071 Málaga, Spain

  17. PairAudit: Guiding Human Review with Graph Tokens under Distribution Shift

    Oct 7, 2026Jiran Tao, Binyan JiangGraph-Based Anomaly DetectionNetwork Intrusion Detection

    The Hong Kong Polytechnic University

  18. ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection

    Oct 5, 2026Elijah Bolluyt, Cristina ComaniciuPrototype-Based ClassificationMahalanobis Distance

    Stevens Institute of Technology, Hoboken, NJ, 07030, USA

  19. Benchmarking candidate coverage and rejection policy transfer in typed decision models

    Oct 2, 2026Jiawen Lu, Tongtong WuLLM EvaluationSelective Prediction

    Monash University

  20. Robust Evidential Learning Through Latent Consistency

    Oct 1, 2026Charmaine Barker, Daniel Bethell, Simos GerasimouEvidential Deep LearningAdversarial Robustness

    Department of Computer Science, University of York, UK · Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus

  21. Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain

    Oct 1, 2026Donghoon Lee, Shinjin KangDistribution Shift DetectionOOD Detection

    Hongik University

  22. Vmem-φ\varphi: Low-Compute Out-of-Distribution Detection in Spiking Neural Networks from Membrane-Potential Statistics

    Sep 29, 2026Arul Rana, Agrim Tripathi, Shoaib Ahmed Dipu +3OOD DetectionSpiking Neural Networks

    Indian Institute of Technology Kharagpur · Indiana University Indianapolis · Bangladesh University of Engineering and Technology +1

  23. A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion

    Sep 28, 2026Fred Xu, Thomas Markovich, Florence Regol +1Graph Neural NetworksUncertainty Quantification

    Department of Computer Science University of California, Los Angeles · Block, Inc. · Mila, Quebec AI Institute

  24. Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One Year

    Sep 25, 2026Mahmoud AbbasiEncrypted Traffic ClassificationKnowledge Distillation

    University of Salamanca, Salamanca, Spain · AIR Institute, Salamanca, Spain

  25. Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures

    Sep 19, 2026Mohammed Ahnouch, Lotfi ElaachakFeature WhiteningOOD Detection

    Université Paris 1 Paris, France · Faculty of Science and Technology of Tangier Abdelmalek Essaadi University Tangier, Morocco

  26. Combining Foundation Model Confidence and Monocular Depth for Training-Free Out-of-Distribution Segmentation

    Sep 19, 2026Serin Varghese, Fabian Hüger, Kira MaagOOD DetectionSegmentation Uncertainty Estimation

    CARIAD SE Wolfsburg, Germany

  27. Local Sparsity Enables Unsupervised LLM Safety Detection

    Sep 17, 2026Xin Chen, Gil Kur, Alexander Shevchenko +1Sparse AutoencodersLLM Safety Monitoring

    ETH Zürich

  28. RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation

    Sep 16, 2026Loris Schneider, Edgar Welte, Rania RayyesRobot Failure DetectionFault Detection

    Institute for Material Handling and Logistics (IFL), Karlsruhe Institute of Technology, 76131, Germany.

  29. Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification

    Sep 15, 2026Ch Muhammad Awais, Marco Reggiannini, Davide Moroni +1ClassificationCross-Dataset Generalization

    Institute of Science and Technology, National Research Council, Pisa, Italy

  30. Operational Range Bounding in Spectroscopy: A Safety Cage Framework for Machine Learning Models

    Sep 11, 2026Nikki Grens, Luís F. Simões, Kai Hou Yip +1Scientific MLSelective Prediction

    ML Analytics, 2660-329 Lisbon, Portugal · Department of Space Engineering, Delft University of Technology, 2600 AA Delft, The Netherlands · Department of Physics, King’s College London, University of London, WC2R 2LS, London, United Kingdom +1