mlsanityData to 7 Oct 2026

Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability

arXiv 2210.08210 ↗First posted 15 Oct 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes a self-explainable Deep Learning (SE-DL) system for an image classification problem that performs self-error detection. The self-error detection is key to improving the DL system's safe operation, especially in safety-critical applications such as automotive systems. A SE-DL system outputs both the class prediction and an explanation for that prediction, which provides insight into how the system makes its predictions for humans. Additionally, we leverage the explanation of the proposed SE-DL system to detect potential class prediction errors of the system. The proposed SE-DL system uses a set of concepts to generate the explanation. The concepts are human-understandable lower-level image features in each input image relevant to the higher-level class of that image. We present a concept selection methodology for scoring all concepts and selecting a subset of them based on their contribution to the error detection performance of the proposed SE-DL system. Finally, we present different error detection schemes using the proposed SE-DL system to compare them against an error detection scheme without any SE-DL system.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 15 Oct 2022.

Builds on

21 of 38 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  5. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  6. 2017The (Un)reliability of saliency methodscited by 331
  7. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  8. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  9. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  10. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  11. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  12. 2018The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approachescited by 74
9 more
  1. 2019Interpretable and Steerable Sequence Learning via Prototypescited by 72
  2. 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
  3. 2019Deep Learning for Large-Scale Traffic-Sign Detection and Recognitioncited by 34
  4. 2020EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attackscited by 28
  5. 2016Engineering Safety in Machine Learningcited by 24
  6. 2020Self-explaining AI as an alternative to interpretable AIcited by 18
  7. 2019Communication-Efficient Jaccard Similarity for High-Performance Distributed Genome Comparisonscited by 10
  8. 2019Cross-Layer Strategic Ensemble Defense Against Adversarial Examplescited by 7
  9. 2020Teaching the Machine to Explain Itself using Domain Knowledgecited by 6

Built on by

Not cited yet.