mlsanityData to 7 Oct 2026

Energy-based Out-of-distribution Detection

arXiv 2010.03759 ↗First posted 8 Oct 2020cs.LG cs.AIcited by 1,296

Not on the map. Why?

Cited by 60 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density of the inputs and are less susceptible to the overconfidence issue. Within this framework, energy can be flexibly used as a scoring function for any pre-trained neural classifier as well as a trainable cost function to shape the energy surface explicitly for OOD detection. On a CIFAR-10 pre-trained WideResNet, using the energy score reduces the average FPR (at TPR 95%) by 18.03% compared to the softmax confidence score. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.

Key facts. Cited by 1,296 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 72; 2022: 157; 2023: 254; 2024: 290; 2025: 271; 2026: 252.

1,296 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  5. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  6. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  7. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  8. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  9. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  10. 2021Towards Open World Object Detectioncited by 297
  11. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  12. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
38 more
  1. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  2. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  3. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  4. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  5. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  6. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  7. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  8. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  11. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  12. 2023Non-Parametric Outlier Synthesiscited by 129
  13. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  14. 2023A Unified Continual Learning Framework with General Parameter-Efficient Tuningcited by 124
  15. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  16. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  17. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  18. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  19. 2021Can multi-label classification networks know what they don't know?cited by 100
  20. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 100
  21. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  22. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  23. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  24. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  25. 2021Constraints Penalized Q-learning for Safe Offline Reinforcement Learningcited by 90
  26. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  27. 2022Training OOD Detectors in their Natural Habitatscited by 86
  28. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  29. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 81
  30. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  31. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  32. 2022A Theoretical Study on Solving Continual Learningcited by 78
  33. 2024Process Reward Model with Q-Value Rankingscited by 78
  34. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  35. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  36. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
  37. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  38. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68

50 most cited of 1,296 All 1,296 (JSON)