mlsanityData to 14 Oct 2026

Classification Uncertainty of Deep Neural Networks Based on Gradient Information

arXiv 1805.08440 ↗First posted 22 May 2018cs.LG cs.AI cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification accuracy -- i.e. the task of classifying predictions as correct or incorrect without knowing the actual label -- as for entropy thresholding. We apply meta classification to unknown concepts (out-of-distribution samples) -- EMNIST/Omniglot letters, CIFAR10 and noise -- and demonstrate that meta classification rates for unknown concepts can be increased when using entropy together with several gradient based metrics as input quantities for a meta classifier. Meta classifiers only trained on the uncertainty metrics of known concepts, i.e. EMNIST digits, usually do not perform equally well for all unknown concepts. If we however allow the meta classifier to be trained on uncertainty metrics for some out-of-distribution samples, meta classification for concepts remote from EMNIST digits (then termed known unknowns) can be improved considerably.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 3; 2023: 12; 2024: 7; 2025: 4; 2026: 3.

43 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 81
  3. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  4. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 41
  5. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  6. 2023Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensemblescited by 30
  7. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  8. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  9. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  10. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  11. 2023Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothnesscited by 15
  12. 2022Gradient-Based Adversarial and Out-of-Distribution Detectioncited by 14
31 more
  1. 2021Resisting Out-of-Distribution Data Problem in Perturbation of XAIcited by 12
  2. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  3. 2024A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learningcited by 10
  4. 2021Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applicationscited by 9
  5. 2021Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learningcited by 9
  6. 2021WOOD: Wasserstein-based Out-of-Distribution Detectioncited by 9
  7. 2023Probing the Purview of Neural Networks via Gradient Analysiscited by 9
  8. 2022Open-Set Recognition with Gradient-Based Representationscited by 7
  9. 2023Learning Complementary Policies for Human-AI Teamscited by 7
  10. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 6
  11. 2025Probabilistic Machine Learning for Noisy Labels in Earth Observationcited by 6
  12. 2023Compensation Learning in Semantic Segmentationcited by 5
  13. 2021Exploring the Limits of Epistemic Uncertainty Quantification in Low-Shot Settingscited by 4
  14. 2025Uncertainty-Aware Deep Learning for Wildfire Danger Forecastingcited by 4
  15. 2024Understanding the Dependence of Perception Model Competency on Regions in an Imagecited by 3
  16. 2024Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Modelscited by 3
  17. 2023Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applicationscited by 2
  18. 2023Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimatescited by 2
  19. 2021Fast whole-slide cartography in colon cancer histology using superpixels and CNN classificationcited by 1
  20. 2023Uncertainty quantification for deep learning-based schemes for solving high-dimensional backward stochastic differential equationscited by 1
  21. 2024Uncertainty Driven Active Learning for Image Segmentation in Underwater Inspectioncited by 1
  22. 2024Context-Based Echo State Networks with Prediction Confidence for Human-Robot Shared Controlcited by 1
  23. 2025Focus on Likely Classes for Test-Time Predictioncited by 1
  24. 2021Graceful Degradation and Related Fieldscited by 0
  25. 2021Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognitioncited by 0
  26. 2021Latent Cognizance: What Machine Really Learnscited by 0
  27. 2023GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformationscited by 0
  28. 2023Uncertainty Quantification using Generative Approachcited by 0
  29. 2026How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustnesscited by 0
  30. 2026Revisiting Neural Activation Coverage for Uncertainty Estimationcited by 0
  31. 2026MetaErr: Towards Predicting Error Patterns in Deep Neural Networkscited by 0