mlsanityData to 14 Oct 2026

On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques

arXiv 2403.15497 ↗First posted 21 Mar 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 38 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

19 of 38 references.

References · 19

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 2016Concrete Problems in AI Safetycited by 1,642
  5. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  8. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  9. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  10. 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
  11. 2017Resilience: A Criterion for Learning in the Presence of Arbitrary Outlierscited by 43
  12. 2019Outside the Box: Abstraction-Based Monitoring of Neural Networkscited by 36
7 more
  1. 2021A statistical framework for efficient out of distribution detection in deep neural networkscited by 28
  2. 2019Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Outputcited by 20
  3. 2022Detection of out-of-distribution samples using binary neuron activation patternscited by 15
  4. 2020On the use of Benford's law to detect GAN-generated imagescited by 11
  5. 2022Out-of-Distribution Detection with Class Ratio Estimationcited by 4
  6. 2020Explaining Predictions of Deep Neural Classifier via Activation Analysiscited by 3
  7. 2021Rethinking Neural Networks With Benford's Lawcited by 2

Built on by

Not cited yet.