mlsanityData to 7 Oct 2026

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

arXiv 2202.01197 ↗First posted 2 Feb 2022cs.LG cs.CVcited by 300

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training. Specifically, VOS samples virtual outliers from the low-likelihood region of the class-conditional distribution estimated in the feature space. Alongside, we introduce a novel unknown-aware training objective, which contrastively shapes the uncertainty space between the ID data and synthesized outlier data. VOS achieves competitive performance on both object detection and image classification models, reducing the FPR95 by up to 9.36% compared to the previous best method on object detectors. Code is available at https://github.com/deeplearning-wisc/vos.

Key facts. Cited by 300 papers in the map (data through 7 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

46 of 61 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2016Wide Residual Networkscited by 3,057
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2013Describing Textures in the Wildcited by 2,110
  11. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
34 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  5. 2020Designing Network Design Spacescited by 954
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  11. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  13. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  14. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  15. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  16. 2021Towards Open World Object Detectioncited by 297
  17. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  18. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  19. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  20. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  21. 2020Incremental Few-Shot Object Detectioncited by 102
  22. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  23. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  24. 2020Incremental Object Detection via Meta-Learningcited by 58
  25. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  26. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  27. 2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
  28. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  29. 2020Dense open-set recognition with synthetic outliers generated by Real NVPcited by 29
  30. 2021Robust Object Detection via Instance-Level Temporal Cycle Confusioncited by 24
  31. 2021Monte Carlo DropBlock for Modelling Uncertainty in Object Detectioncited by 20
  32. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  33. 2021Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Losscited by 11
  34. 2020Multi-Task Incremental Learning for Object Detectioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 33; 2023: 75; 2024: 88; 2025: 65; 2026: 39.

300 papers.

Sort:

By area:

  1. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  2. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  3. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  4. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  5. 2023Non-Parametric Outlier Synthesiscited by 129
  6. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  7. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  8. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  9. 2022Training OOD Detectors in their Natural Habitatscited by 86
  10. 2024Process Reward Model with Q-Value Rankingscited by 78
  11. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  12. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
38 more
  1. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  2. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  3. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  4. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 42
  5. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  6. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  7. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  8. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  9. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  10. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  11. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  12. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  13. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  14. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  15. 2022Augmenting Softmax Information for Selective Classification with Out-of-Distribution Datacited by 27
  16. 2022Towards Open Set Video Anomaly Detectioncited by 26
  17. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  18. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23
  19. 2023Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objectscited by 23
  20. 2024ConjNorm: Tractable Density Estimation for Out-of-Distribution Detectioncited by 22
  21. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  22. 2025Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentationcited by 21
  23. 2024Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalizationcited by 20
  24. 2024Robust Semi-supervised Learning by Wisely Leveraging Open-set Datacited by 20
  25. 2023Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detectioncited by 19
  26. 2024Self-Guided Generation of Minority Samples Using Diffusion Modelscited by 19
  27. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  28. 2022Latent Discriminant deterministic Uncertaintycited by 17
  29. 2022Open-Set Semi-Supervised Object Detectioncited by 17
  30. 2023Class Incremental Learning via Likelihood Ratio Based Task Predictioncited by 17
  31. 2024Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalizationcited by 17
  32. 2023Perception Datasets for Anomaly Detection in Autonomous Driving: A Surveycited by 16
  33. 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognitioncited by 16
  34. 2023Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detectioncited by 16
  35. 2023Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capabilitycited by 16
  36. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  37. 2023VRA: Variational Rectified Activation for Out-of-distribution Detectioncited by 15
  38. 2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 15

50 most cited of 300 All 300 (JSON)