mlsanityData to 13 Oct 2026

ViM: Out-Of-Distribution with Virtual-logit Matching

arXiv 2203.10807 ↗First posted 21 Mar 2022cs.CVcited by 405

Not on the map. Why?

Cited by 27 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Most of the existing Out-Of-Distribution (OOD) detection algorithms depend on single input source: the feature, the logit, or the softmax probability. However, the immense diversity of the OOD examples makes such methods fragile. There are OOD samples that are easy to identify in the feature space while hard to distinguish in the logit space and vice versa. Motivated by this observation, we propose a novel OOD scoring method named Virtual-logit Matching (ViM), which combines the class-agnostic score from feature space and the In-Distribution (ID) class-dependent logits. Specifically, an additional logit representing the virtual OOD class is generated from the residual of the feature against the principal space, and then matched with the original logits by a constant scaling. The probability of this virtual logit after softmax is the indicator of OOD-ness. To facilitate the evaluation of large-scale OOD detection in academia, we create a new OOD dataset for ImageNet-1K, which is human-annotated and is 8.8x the size of existing datasets. We conducted extensive experiments, including CNNs and vision transformers, to demonstrate the effectiveness of the proposed ViM score. In particular, using the BiT-S model, our method gets an average AUROC 90.91% on four difficult OOD benchmarks, which is 4% ahead of the best baseline. Code and dataset are available at https://github.com/haoqiwang/vim.

Key facts. Cited by 405 papers in the map (data through 13 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

30 of 42 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,574
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  5. 2013Describing Textures in the Wildcited by 2,115
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,475
  7. 2019Natural Adversarial Examplescited by 1,405
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,297
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 941
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 799
  12. 2019Big Transfer (BiT): General Visual Representation Learningcited by 768
18 more
  1. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 674
  2. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  3. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  4. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  5. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  6. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  7. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  10. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  11. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  12. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  13. 2018Reducing Network Agnostophobiacited by 165
  14. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  15. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  16. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  17. 2020Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Featurescited by 20
  18. 2020Outlier Detection through Null Space Analysis of Neural Networkscited by 19

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 18; 2023: 90; 2024: 109; 2025: 107; 2026: 81.

405 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 598
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  3. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  4. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 133
  5. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  6. 2023Non-Parametric Outlier Synthesiscited by 129
  7. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  8. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  9. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  10. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  11. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  12. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
38 more
  1. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 59
  2. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  3. 2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
  4. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  5. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  6. 2022Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interferencecited by 44
  7. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  8. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  9. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 41
  10. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  11. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  12. 2023GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detectioncited by 36
  13. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  14. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  15. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  16. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 33
  17. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  18. 2024COME: Test-time adaption by Conservatively Minimizing Entropycited by 31
  19. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 31
  20. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  21. 2023Provably Bounding Neural Network Preimagescited by 29
  22. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  23. 2023Learnability and Algorithm for Continual Learningcited by 28
  24. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  25. 2022Augmenting Softmax Information for Selective Classification with Out-of-Distribution Datacited by 27
  26. 2023Simplicity Bias in 1-Hidden Layer Neural Networkscited by 26
  27. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 26
  28. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 25
  29. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 25
  30. 2023Improving Selective Visual Question Answering by Learning from Your Peerscited by 24
  31. 2024Kernel PCA for Out-of-Distribution Detectioncited by 24
  32. 2022Out-Of-Distribution Detection Is Not All You Needcited by 23
  33. 2023IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilizationcited by 23
  34. 2023ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithmscited by 22
  35. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Modelcited by 22
  36. 2024Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domainscited by 21
  37. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Modelscited by 21
  38. 2025Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learningcited by 21

50 most cited of 405 All 405 (JSON)