Data to 7 Oct 2026

Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers

arXiv 1809.03576 ↗First posted 4 Sep 2018cs.LG cs.CV stat.MLcited by 126

Not on the map. Why?

Abstract (arXiv)

As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin m between the average entropy of the OOD and in-distribution samples. In conjunction with the standard cross-entropy loss, we minimize the novel loss to train an ensemble of classifiers. We also propose a novel method to combine the outputs of the ensemble of classifiers to obtain OOD detection score and class prediction. Overall, our method convincingly outperforms Hendrycks et al.[7] and the current state-of-the-art ODIN[13] on several OOD detection benchmarks.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 36; 2023: 20; 2024: 20; 2025: 8; 2026: 7.

126 papers.

Sort:

By area:

2021Generalized Out-of-Distribution Detection: A Surveycited by 796
2021A Survey of Uncertainty in Deep Neural Networkscited by 675
2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 247
2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
2021Semantically Coherent Out-of-Distribution Detectioncited by 107
2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
2021An Improved Baseline for Sentence-level Relation Extractioncited by 80
2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
2022Full-Spectrum Out-of-Distribution Detectioncited by 63

38 more

2022Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detectioncited by 59
2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 52
2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
2025Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policiescited by 49
2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
2021Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networkscited by 37
2025Failure Prediction at Runtime for Generative Robot Policiescited by 36
2022Uncertainty Estimation for Language Reward Modelscited by 35
2023A Survey on Out-of-Distribution Detection in NLPcited by 31
2023Learning on Graphs with Out-of-Distribution Nodescited by 29
2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
2021An Effective Baseline for Robustness to Distributional Shiftcited by 25
2021Transformaly -- Two (Feature Spaces) Are Better Than Onecited by 25
2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
2021Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detectioncited by 23
2022Few-shot Learning with Noisy Labelscited by 23
2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
2022Interpretable Self-Aware Neural Networks for Robust Trajectory Predictioncited by 22
2024Open-World Semantic Segmentation Including Class Similaritycited by 22
2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
2021Knowing the No-match: Entity Alignment with Dangling Casescited by 20
2021GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentationcited by 20
2022Igeood: An Information Geometry Approach to Out-of-Distribution Detectioncited by 20
2021Learning to Track Instances without Video Annotationscited by 18
2022Out-of-Distribution Detection for LiDAR-based 3D Object Detectioncited by 17
2025Adversarial Training of Reward Modelscited by 17
2022Curved Geometric Networks for Visual Anomaly Recognitioncited by 15
2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
2023Towards Semi-supervised Universal Graph Classificationcited by 15
2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
2021CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issuecited by 14
2021Addressing out-of-distribution label noise in webly-labelled datacited by 14
2022RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detectioncited by 13
2024STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replaycited by 13
2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
2021Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Losscited by 11
2022Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penaltycited by 11
2026Foundational World Models Accurately Detect Bimanual Manipulator Failurescited by 11

50 most cited of 126 All 126 (JSON)