Data to 7 Oct 2026

Contrastive Training for Improved Out-of-Distribution Detection

arXiv 2007.05566 ↗First posted 10 Jul 2020cs.LG stat.MLcited by 186

Not on the map. Why?

Abstract (arXiv)

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 51; 2023: 37; 2024: 27; 2025: 19; 2026: 12.

186 papers.

Sort:

By area:

2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92

38 more

2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
2022Evaluation Gaps in Machine Learning Practicecited by 48
2022Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognitioncited by 44
2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
2022Robust and Efficient Medical Imaging with Self-Supervisioncited by 40
2022Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positivescited by 37
2023Continuous Learning for Android Malware Detectioncited by 33
2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
2022Watermarking for Out-of-distribution Detectioncited by 28
2021A statistical framework for efficient out of distribution detection in deep neural networkscited by 27
2021OODformer: Out-Of-Distribution Detection Transformercited by 27
2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
2022Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcitycited by 24
2021Masked Contrastive Learning for Anomaly Detectioncited by 23
2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
2023A Message Passing Perspective on Learning Dynamics of Contrastive Learningcited by 22
2021Video Class Agnostic Segmentation Benchmark for Autonomous Drivingcited by 21
2022Igeood: An Information Geometry Approach to Out-of-Distribution Detectioncited by 20
2021A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networkscited by 19
2023Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detectioncited by 19
2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
2024Contrastive Instruction Tuningcited by 17
2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
2023Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localizationcited by 16
2023EAT: Towards Long-Tailed Out-of-Distribution Detectioncited by 16
2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
2025Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learningcited by 16

50 most cited of 186 All 186 (JSON)