mlsanityData to 14 Oct 2026

Deep Anomaly Detection with Outlier Exposure

arXiv 1812.04606 ↗First posted 11 Dec 2018cs.LG cs.CL cs.CVcited by 942

Not on the map. Why?

Cited by 25 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small- and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

Key facts. Cited by 942 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 172; 2022: 188; 2023: 193; 2024: 157; 2025: 140; 2026: 91.

942 papers.

Sort:

By area:

  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  2. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  3. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  4. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  5. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  6. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  7. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  8. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  9. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  10. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  11. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  12. 2021Unsolved Problems in ML Safetycited by 292
38 more
  1. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  3. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  4. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  5. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  6. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  7. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  8. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  9. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  10. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  11. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  12. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  13. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  14. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  15. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  16. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  17. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  18. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  19. 2023Non-Parametric Outlier Synthesiscited by 129
  20. 2021Predicting with Confidence on Unseen Distributionscited by 116
  21. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  22. 2022Multimodal Masked Autoencoders Learn Transferable Representationscited by 109
  23. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  24. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  25. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  26. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  27. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  28. 2022Denoising diffusion models for out-of-distribution detectioncited by 104
  29. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  30. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  31. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  32. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  33. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  34. 2022Training OOD Detectors in their Natural Habitatscited by 86
  35. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 85
  36. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  37. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  38. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80

50 most cited of 942 All 942 (JSON)