mlsanityData to 7 Oct 2026

MOOD: Multi-level Out-of-distribution Detection

arXiv 2104.14726 ↗First posted 30 Apr 2021cs.CVcited by 94

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment. While improved OOD detection methods have emerged, they often rely on the final layer outputs and require a full feedforward pass for any given input. In this paper, we propose a novel framework, multi-level out-of-distribution detection MOOD, which exploits intermediate classifier outputs for dynamic and efficient OOD inference. We explore and establish a direct relationship between the OOD data complexity and optimal exit level, and show that easy OOD examples can be effectively detected early without propagating to deeper layers. At each exit, the OOD examples can be distinguished through our proposed adjusted energy score, which is both empirically and theoretically suitable for networks with multiple classifiers. We extensively evaluate MOOD across 10 OOD datasets spanning a wide range of complexities. Experiments demonstrate that MOOD achieves up to 71.05% computational reduction in inference, while maintaining competitive OOD detection performance.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

35 of 56 references.

References · 35

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
23 more
  1. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 479
  2. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  3. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  4. 2018Deep Learning for Classical Japanese Literaturecited by 415
  5. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  6. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  7. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  8. 2014Deeply-Supervised Netscited by 364
  9. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  10. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  11. 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
  12. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  13. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  14. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  15. 2017Adaptive Neural Networks for Efficient Inferencecited by 161
  16. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  17. 2016Spatially Adaptive Computation Time for Residual Networkscited by 118
  18. 2019Improved Techniques for Training Adaptive Deep Networkscited by 66
  19. 2017Dynamic Computational Time for Visual Attentioncited by 23
  20. 2018Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognitioncited by 22
  21. 2019Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Outputcited by 20
  22. 2017Recurrent Segmentation for Variable Computational Budgetscited by 3
  23. 2018Depth-Adaptive Computational Policies for Efficient Visual Trackingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 21; 2023: 27; 2024: 17; 2025: 9; 2026: 10.

94 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. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  4. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  5. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  6. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  7. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  8. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  9. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  10. 2021Can multi-label classification networks know what they don't know?cited by 100
  11. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  12. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
38 more
  1. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  2. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  3. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  4. 2022OpenCon: Open-world Contrastive Learningcited by 33
  5. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  6. 2023Improving Selective Visual Question Answering by Learning from Your Peerscited by 24
  7. 2022Out-of-Distribution Detection with Semantic Mismatch under Maskingcited by 22
  8. 2023GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradientscited by 21
  9. 2022Concept-based Explanations for Out-Of-Distribution Detectorscited by 16
  10. 2023Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detectioncited by 16
  11. 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capabilitycited by 16
  12. 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
  13. 2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 15
  14. 2023How Good Are LLMs at Out-of-Distribution Detection?cited by 15
  15. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  16. 2021Hyperdimensional Feature Fusion for Out-Of-Distribution Detectioncited by 13
  17. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  18. 2024STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replaycited by 13
  19. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  20. 2021Label-Free Model Evaluation with Semi-Structured Dataset Representationscited by 10
  21. 2023Meta OOD Learning for Continuously Adaptive OOD Detectioncited by 10
  22. 2022Heatmap-based Out-of-Distribution Detectioncited by 9
  23. 2023Adaptive Deep Neural Network Inference Optimization with EENetcited by 9
  24. 2022Boosting Out-of-Distribution Detection with Multiple Pre-trained Modelscited by 7
  25. 2024A Layer Selection Approach to Test Time Adaptationcited by 7
  26. 2022READ: Aggregating Reconstruction Error into Out-of-distribution Detectioncited by 6
  27. 2022A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptionscited by 6
  28. 2024CLIP-driven Outliers Synthesis for few-shot OOD detectioncited by 6
  29. 2024Out-Of-Distribution Detection with Diversification (Provably)cited by 6
  30. 2025Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detectioncited by 6
  31. 2023DeepLens: Interactive Out-of-distribution Data Detection in NLP Modelscited by 5
  32. 2023Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detectioncited by 5
  33. 2022Understanding the Robustness of Multi-Exit Models under Common Corruptionscited by 4
  34. 2023Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustnesscited by 4
  35. 2023Toward Auto-evaluation with Confidence-based Category Relation-aware Regressioncited by 4
  36. 2025Understanding Knowledge Transferability for Transfer Learning: A Surveycited by 4
  37. 2025Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 4
  38. 2025BOOD: Boundary-based Out-Of-Distribution Data Generationcited by 4

50 most cited of 94 All 94 (JSON)