Open-Set Recognition

Ask about this topic

Overview

Open-set recognition studies how models can classify known categories without forcing unfamiliar inputs into those categories, a need in settings such as medical diagnosis, security, and ecological monitoring. Common approaches use calibrated confidence, energy or distance scores, metric learning and prototypes; newer systems also use vision-language models, retrieval, and explicit negative examples. Work spans images, video, audio, text, biometrics, and object detection, with methods for rejecting unknowns as well as discovering and learning new classes. A central challenge is balancing accurate known-class predictions with reliable rejection under domain shift, while calibrating thresholds and evaluating them without access to representative unknown data.

Latest papers

CardsList

69 papers9 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

  1. Uncertainty Estimation for the Open-Set Text Classification systems

    Mar 17, 2026Leonid Erlygin, Alexey ZaytsevUncertainty QuantificationOpen-Set Recognition

    Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · Risk Management, Sber, Moscow, Russia

  2. MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition

    Mar 17, 2026Hyejeong Im, Wonseon Lim, Dae-Won KimContinual LearningEgocentric Video Understanding

    Department of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea.

  3. Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning

    Mar 9, 2026Chen-Chen Zong, Yu-Qi Chi, Xie-Yang Wang +2Active LearningOpen-Set Recognition

    Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China

  4. A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination

    Mar 4, 2026Stefano Berti, Giulia Pasquale, Lorenzo NataleOpen-Set RecognitionFew-Shot Learning

    Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genoa, Italy

  5. Seeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding

    Mar 4, 2026Junhan Chen, Zilu Zhou, Yujun Tong +3Fine-Grained Visual PerceptionVisually Grounded Reasoning

    School of Artificial Intelligence, Beijing University of Posts and Telecommunications, China

  6. Overview of the CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification

    Feb 25, 2026Hexin Dong, Yi Lin, Pengyu Zhou +7Chest X-Ray ClassificationMedical Image Benchmarks

    Weill Cornell Medicine · Peking Union Medical College · University of Minnesota +2

  7. HyDRA: A Hybrid Dual-Mode Network for Closed- and Open-Set RFFI with Optimized VMD

    Jul 16, 2025Hanwen Liu, Yuhe Huang, Yifeng Gong +2Hybrid CNN-Transformer ArchitecturesRF Fingerprint Identification

    School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, 518107, China

  8. XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition

    Mar 3, 2024Kun-Yu Lin, Henghui Ding, Jia-Run Du +6Open-Set RecognitionCross-Domain Generalization

    School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510275, China · Institute of Big Data, Fudan University, Shanghai 200433, China · AI Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China +1

  9. MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration

    Nov 20, 2022Zongyao Lyu, Nolan B. Gutierrez, William J. BeksiProbability CalibrationOpen-Set Recognition

    The University of Texas at Arlington Arlington, TX, USA