mlsanityData to 14 Oct 2026

Detection of out-of-distribution samples using binary neuron activation patterns

arXiv 2212.14268 ↗First posted 29 Dec 2022cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNN) have outstanding performance in various applications. Despite numerous efforts of the research community, out-of-distribution (OOD) samples remain a significant limitation of DNN classifiers. The ability to identify previously unseen inputs as novel is crucial in safety-critical applications such as self-driving cars, unmanned aerial vehicles, and robots. Existing approaches to detect OOD samples treat a DNN as a black box and evaluate the confidence score of the output predictions. Unfortunately, this method frequently fails, because DNNs are not trained to reduce their confidence for OOD inputs. In this work, we introduce a novel method for OOD detection. Our method is motivated by theoretical analysis of neuron activation patterns (NAP) in ReLU-based architectures. The proposed method does not introduce a high computational overhead due to the binary representation of the activation patterns extracted from convolutional layers. The extensive empirical evaluation proves its high performance on various DNN architectures and seven image datasets.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 29 Dec 2022.

Builds on

31 of 55 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
19 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  5. 2015Towards Open Set Deep Networkscited by 538
  6. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  7. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  8. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  9. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  10. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  11. 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 161
  12. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  13. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  14. 2019Outside the Box: Abstraction-Based Monitoring of Neural Networkscited by 36
  15. 2018Runtime Monitoring Neuron Activation Patternscited by 34
  16. 2019Activation Analysis of a Byte-Based Deep Neural Network for Malware Classificationcited by 14
  17. 2020Stationary Activations for Uncertainty Calibration in Deep Learningcited by 14
  18. 2019Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Unitscited by 3
  19. 2020Explaining Predictions of Deep Neural Classifier via Activation Analysiscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 2; 2026: 2.

15 papers.

Sort:

  1. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  2. 2024Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detectioncited by 12
  3. 2024Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observationcited by 10
  4. 2025AdaSCALE: Adaptive Scaling for OOD Detectioncited by 7
  5. 2024Out-of-Distribution Detection using Neural Activation Priorcited by 2
  6. 2024Monitizer: Automating Design and Evaluation of Neural Network Monitorscited by 2
  7. 2023Runtime Monitoring DNN-Based Perceptioncited by 1
  8. 2023Improving Out-of-Distribution Detection with Disentangled Foreground and Background Featurescited by 0
  9. 2023Detecting Out-of-distribution Objects Using Neuron Activation Patternscited by 0
  10. 2023Distilling the Unknown to Unveil Certaintycited by 0
  11. 2024On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniquescited by 0
  12. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
3 more
  1. 2025LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layerscited by 0
  2. 2026A New Framework to Analyse the Distributional Robustness of Deep Neural Networkscited by 0
  3. 2026Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detectioncited by 0