mlsanityData to 14 Oct 2026

ReAct: Out-of-distribution Detection With Rectified Activations

arXiv 2111.12797 ↗First posted 24 Nov 2021cs.LGcited by 486

Not on the map. Why?

Cited by 24 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 practical importance in enhancing the safe deployment of neural networks. One of the primary challenges is that models often produce highly confident predictions on OOD data, which undermines the driving principle in OOD detection that the model should only be confident about in-distribution samples. In this work, we propose ReAct--a simple and effective technique for reducing model overconfidence on OOD data. Our method is motivated by novel analysis on internal activations of neural networks, which displays highly distinctive signature patterns for OOD distributions. Our method can generalize effectively to different network architectures and different OOD detection scores. We empirically demonstrate that ReAct achieves competitive detection performance on a comprehensive suite of benchmark datasets, and give theoretical explication for our method's efficacy. On the ImageNet benchmark, ReAct reduces the false positive rate (FPR95) by 25.05% compared to the previous best method.

Key facts. Cited by 486 papers in the map (data through 14 Oct 2026). Builds on 45 of its 63 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

45 of 63 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2013Describing Textures in the Wildcited by 2,125
  10. 2016Density estimation using Real NVPcited by 2,042
  11. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  12. 2018Group Normalizationcited by 1,524
33 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  2. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2014How transferable are features in deep neural networks?cited by 1,225
  8. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  9. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  10. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  11. 2015Towards Open Set Deep Networkscited by 538
  12. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  13. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  14. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  15. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  16. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  17. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  18. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  19. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  20. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 220
  21. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  22. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  23. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  24. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  25. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  26. 2021Can multi-label classification networks know what they don't know?cited by 100
  27. 2018On the importance of single directions for generalizationcited by 99
  28. 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
  29. 2016Stacked Generative Adversarial Networkscited by 44
  30. 2021Online Adaptation to Label Distribution Shiftcited by 44
  31. 2018Revisiting the Importance of Individual Units in CNNs via Ablationcited by 32
  32. 2020Further Analysis of Outlier Detection with Deep Generative Modelscited by 31
  33. 2019Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 57; 2023: 111; 2024: 130; 2025: 99; 2026: 85.

486 papers.

Sort:

By area:

  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  3. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  4. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  5. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  6. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  7. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  8. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  9. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 184
  10. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  11. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  12. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
38 more
  1. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  2. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  3. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  4. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  5. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  6. 2022Training OOD Detectors in their Natural Habitatscited by 86
  7. 2024Process Reward Model with Q-Value Rankingscited by 80
  8. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  9. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  10. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  11. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  12. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  13. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  14. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  15. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  16. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  17. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 49
  18. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  19. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  20. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  21. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  22. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  23. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  24. 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
  25. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  26. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  27. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  28. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  29. 2023AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challengecited by 35
  30. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  31. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 34
  32. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  33. 2022OpenCon: Open-world Contrastive Learningcited by 33
  34. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  35. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 32
  36. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  37. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  38. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29

50 most cited of 486 All 486 (JSON)