OOD Detection

OOD: Out-of-Distribution

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 11% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 145

All topics

Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
May 22, 2026Bo Peng, Jie Lu, Guangquan Zhang +1Hard Negative Mining OOD Detection
University of Technology Sydney
The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
May 21, 2026Philipp Bomatter, Jack Geary, Henry GoukDistribution Shift Detection OOD Detection
School of Informatics, University of Edinburgh
Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
May 20, 2026Dylan Feng, Pragya Srivastava, Anca Dragan +1Language Model Safety Evaluation LLM Guardrails
University of California, Berkeley, USA · 3Google DeepMind, India.
Early High-Frequency Injection for Geometry-Sensitive OOD Detection
May 20, 2026Chuanjie Cheng, Ningkang Peng, Chenxi Liu +3Frequency-Domain Feature Learning OOD Detection
Nanjing Normal University
Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection
May 19, 2026Neelkamal BhuyanDiffusion-Based OOD Detection Distribution Shift Detection
Georgia Institute of Technology
MusicDET: Zero-Shot AI-Generated Music Detection
May 18, 2026Chaolei Han, Hongsong Wang, Jie GuiAudio Deepfake Detection AI-Generated Music Detection
School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China · School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China +2
Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns
May 18, 2026Xi Chen, Yingjun Xiao, Gang FangOpen-Set Recognition Classification
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China · School of Artificial Intelligence, Guangzhou University, Guangzhou, China +3
Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
May 18, 2026Ningkang Peng, Xuanming Chen, Yanhui GuDiffusion-Based OOD Detection OOD Detection
Nanjing Normal University
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
May 18, 2026Ningkang Peng, Jingyang Mao, Runhan Zhou +2Learning with Noisy Labels OOD Detection
Nanjing Normal University
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
May 16, 2026Osama Zafar, Alexander Nemecek, Yiqian Zhang +5Data Leakage RAG Security
Dept. of Computer and Data Sciences Case Western Reserve University Cleveland, USA
Community-aware evaluation and threshold calibration for open-set plankton image recognition
May 15, 2026Xi Chen, Eryuan Huang, Yingjun Xiao +1Open-Set Recognition OOD Detection
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, 510006, China · School of Environment, South China Normal University, Guangzhou, China +5
When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition
May 14, 2026Siyang Yao, Erhu Feng, Yubin XiaHallucination in Language Models LLM Hallucination Detection
Shanghai Jiao Tong University Shanghai,China
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
May 14, 2026Donghwan Kim, Hyunsoo YoonMahalanobis Distance Diffusion-Based OOD Detection
Department of Industrial Engineering Yonsei University Seoul, South Korea
What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
May 13, 2026Danny Wang, Ruihong Qiu, Zi HuangGraph Neural Networks OOD Detection
The University of Queensland, Australia.
Domain Restriction via Multi SAE Layer Transitions
May 12, 2026Elias Shaheen, Avi MendelsonLLM Interpretability OOD Detection
Technion – Israel Institute of Technology, Haifa, Israel.
VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
May 12, 2026Aryan Gondkar, Hayder Radha, Yiming DengUncertainty Quantification Information Bottleneck
Nondestructive Evaluation Lab, Department of Electrical and Computer Engineering Michigan State University East Lansing, MI · Department of Electrical and Computer Engineering Michigan State University East Lansing, MI
TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection
May 11, 2026Yifeng Yang, Jubo Feng, Jing Xu +3Test-Time Adaptation OOD Detection
Shanghai Jiao Tong University · University of Electronic Science and Technology of China · Shanghai Artificial Intelligence Laboratory +1
A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection
May 11, 2026Jihyeon Baek, Seunghoon Lee, Gitaek Kwon +1Medical Image Analysis OOD Detection
VUNO Inc.
Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
May 10, 2026Yadang Alexis Rouzoumka, Jean Pinsolle, Eugénie Terreaux +3Diffusion-Based OOD Detection OOD Detection
DEMR, ONERA & SONDRA · Université Paris-Saclay · SONDRA, CentraleSupélec +1
Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification
May 9, 2026Devesh ShahOOD Detection
Independent Researcher
Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
May 8, 2026Boyang Dai, Chaoqi Chen, Yizhou YuOOD Detection
1The University of Hong Kong · 2Shenzhen University · 3Shenzhen Loop Area Institute
Rethinking Vacuity for OOD Detection in Evidential Deep Learning
May 7, 2026Claire McNamaraLLM Evaluation Evidential Deep Learning
∗Accenture Labs · †Trinity College Dublin.
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
May 7, 2026Brett Barkley, Preston Culbertson, David Fridovich-KeilOOD Detection
Department of Electrical and Computer Engineering The University of Texas at Austin Austin, TX, USA · Department of Computer Science Cornell University Ithaca, NY, USA · Department of Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, TX, USA
Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging
May 6, 2026Bernhard Kainz, Johanna P Mueller, Matthew Baugh +1Medical Image Anomaly Detection Anomaly Localization
Dept. AIBE, Friedrich–Alexander University Erlangen–Nürnberg, DE · Department of Computing, Imperial College London, UK · Technical University Munich, DE +1
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
May 6, 2026Qingjun Wang, Hongtu Zhou, Hang Yu +5Diffusion-Based OOD Detection Offline RL
School of Computer Science and Technology, Tongji University, Shanghai, China · MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China · Shanghai Innovation Institute
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
May 5, 2026Maria Stoica, Abdelrahman Hekal, Alessio LomuscioAdversarial Robustness OOD Detection
Imperial College London · Zeroth Research
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
May 5, 2026Marco Mustafa Mohammed, Fatemeh Daneshfar, Pietro LiòEvidential Deep Learning OOD Detection
Department of Computer Engineering, Faculty of Engineering, University of Kurdistan, Sanandaj, Iran
Geometry over Density: Few-Shot Cross-Domain OOD Detection
May 5, 2026Shawn Li, You Qin, Jiate Li +4Diffusion-Based OOD Detection Distribution Shift Detection
University of Southern California · National University of Singapore · Amazon
Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy
May 2, 2026Eleanor QuintDistribution Shift Robustness Ensemble Learning
Department of Computing University of Nebraska–Lincoln Lincoln, NE 68508, USA
GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
May 1, 2026Bruno AbrahaoOOD Detection
NYU Shanghai · Leonard N. Stern School of Business, NYU

May 22, 2026, cs.LGJ/K move · Enter open · S save

Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models

Bo Peng, Jie Lu, Guangquan Zhang, Zhen Fang

University of Technology Sydney

Hard Negative Mining OOD Detection

Open paper AskPDF arXiv

Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vision-language models (VLMs), where a popular pipeline is to detect OOD inputs by examining their affinities between ID labels and negative labels, i.e., those semantically different from ID labels. Due to the unavailability of target OOD labels, existing works predominantly rely on heuristic rules to mine negative labels from unlabeled wild corpus data. Despite the empirical success, we argue that the power of VLM-based OOD detection has yet to be fully unleashed since the notorious false negative problem is far from addressed in the literature. With this motivation, we are interested in addressing the challenge of mining true negative labels for OOD scoring. To this end, we develop a theoretical framework for correcting the sampling bias of negatives labels by indirectly approximating the distribution of negative labels. Perhaps surprisingly, we show that the debiased negative mining can be naturally converted into Monte-Carlo sampling based on ID labels and the unlabeled wild corpus data. Extensive experiments empirically manifest that our method establishes a new state-of-the-art in a variety of OOD detection setups. Code is publicly available at \href{https://github.com/60pen9/Debiased-Negative-Mining-Improves-OOD-Detection-with-Pre-trained-VLMs}{\textcolor{red}{here}}.

Momentum

Related topics

Latest papers 145