mlsanityData to 7 Oct 2026

Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need

arXiv 2302.02615 ↗First posted 6 Feb 2023cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn shortcuts instead of comprehensive representations. In this work, we find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We deeply explore the main contributors of OOD detection and find that reconstruction-based pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset. Specifically, we take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD). Without bells and whistles, MOOD outperforms previous SOTA of one-class OOD detection by 5.7%, multi-class OOD detection by 3.0%, and near-distribution OOD detection by 2.1%. It even defeats the 10-shot-per-class outlier exposure OOD detection, although we do not include any OOD samples for our detection

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 6 Feb 2023.

Builds on

44 of 72 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  11. 2020Supervised Contrastive Learningcited by 2,803
  12. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
32 more
  1. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  2. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  3. 2013Describing Textures in the Wildcited by 2,110
  4. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2016Colorful Image Colorizationcited by 1,113
  11. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  13. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  14. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  15. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  16. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  17. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  18. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  19. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  20. 2019Hidden Trigger Backdoor Attackscited by 359
  21. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  22. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  23. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  24. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  25. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  26. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  27. 2020Classification-Based Anomaly Detection for General Datacited by 210
  28. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  29. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  30. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  31. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
  32. 2020Deep Residual Flow for Out of Distribution Detectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 19; 2025: 13; 2026: 9.

46 papers.

Sort:

By area:

  1. 2024DAPE: Data-Adaptive Positional Encoding for Length Extrapolationcited by 30
  2. 2024Masked Image Modeling: A Surveycited by 28
  3. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  4. 2024Adapting to Distribution Shift by Visual Domain Prompt Generationcited by 23
  5. 2025Secure On-Device Video OOD Detection Without Backpropagationcited by 19
  6. 2024Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervisioncited by 16
  7. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  8. 2023TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentationcited by 14
  9. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  10. 2024A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?cited by 13
  11. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  12. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
34 more
  1. 2024DAPE V2: Process Attention Score as Feature Map for Length Extrapolationcited by 10
  2. 2023BAL: Balancing Diversity and Novelty for Active Learningcited by 9
  3. 2024OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learningcited by 7
  4. 2025Resilient Contrastive Pre-training under Non-Stationary Driftcited by 7
  5. 2024MOODv2: Masked Image Modeling for Out-of-Distribution Detectioncited by 6
  6. 2024Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphscited by 6
  7. 2023Can Pre-trained Networks Detect Familiar Out-of-Distribution Data?cited by 4
  8. 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptationcited by 4
  9. 2025Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimationcited by 3
  10. 2025Revisiting Medical Image Retrieval via Knowledge Consolidationcited by 3
  11. 2023A Hybrid Architecture for Out of Domain Intent Detection and Intent Discoverycited by 2
  12. 2024Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impactcited by 2
  13. 2025Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processescited by 2
  14. 2024Detecting Out-of-Distribution Objects through Class-Conditioned Inpaintingcited by 1
  15. 2024Collaborative Knowledge Distillation via a Learning-by-Education Node Communitycited by 1
  16. 2025DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detectioncited by 1
  17. 2025Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approachcited by 1
  18. 2025Hypercone Assisted Contour Generation for Out-of-Distribution Detectioncited by 1
  19. 2025Multi-label out-of-distribution detection via evidential learningcited by 1
  20. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivitycited by 1
  21. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1
  22. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  23. 2023Adversarial Masked Image Inpainting for Robust Detection of Mpox and Non-Mpoxcited by 0
  24. 2024Two Is Better Than One: Aligned Representation Pairs for Anomaly Detectioncited by 0
  25. 2024Out-of-Distribution Detection with Overlap Indexcited by 0
  26. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  27. 2025Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectoriescited by 0
  28. 2026Native Extrapolation Awareness in Flow-Based Conditional Generationcited by 0
  29. 2026From Misclassifications to Outliers: Joint Reliability Assessment in Classificationcited by 0
  30. 2026A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classificationcited by 0
  31. 2026Learning domain-invariant features through channel-level sparsification for Out-Of Distribution Generalizationcited by 0
  32. 2026Disentangled Graph Prompting for Out-Of-Distribution Detectioncited by 0
  33. 2026Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detectioncited by 0
  34. 2026SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Modelcited by 0