mlsanityData to 14 Oct 2026

Causal Explanations for Image Classifiers

arXiv 2411.08875 ↗First posted 13 Nov 2024cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to find them. However, none of the existing tools use a principled approach based on formal definitions of cause and explanation. In this paper we present a novel black-box approach to computing explanations grounded in the theory of actual causality. We prove relevant theoretical results and present an algorithm for computing approximate explanations based on these definitions. We prove termination of our algorithm and discuss its complexity and the amount of approximation compared to the precise definition. We implemented the framework in a tool ReX and we present experimental results and a comparison with state-of-the-art tools. We demonstrate that ReX is the most efficient black-box tool and produces the smallest explanations, in addition to outperforming other black-box tools on standard quality measures.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 27 of its 60 references that are in the map. First posted on arXiv 13 Nov 2024.

Builds on

27 of 60 references.

References · 27

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  7. 2018Sanity Checks for Saliency Mapscited by 1,156
  8. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  9. 2020Concept Bottleneck Modelscited by 1,032
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  11. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
15 more
  1. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  2. 2018Actionable Recourse in Linear Classificationcited by 328
  3. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  4. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  5. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  6. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
  7. 2020Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same Endcited by 66
  8. 2015A Modification of the Halpern-Pearl Definition of Causalitycited by 47
  9. 2020One Explanation is Not Enough: Structured Attention Graphs for Image Classificationcited by 32
  10. 2022Causal Explanations and XAIcited by 30
  11. 2021Causal Sufficiency and Actual Causationcited by 29
  12. 2024Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Modelscited by 8
  13. 2023MRxaI: Black-Box Explainability for Image Classifiers in a Medical Settingcited by 6
  14. 2013Defining Explanation in Probabilistic Systemscited by 5
  15. 2024Real-Time Incremental Explanations for Object Detectors in Autonomous Drivingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanationscited by 13
  2. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  3. 2025SpecReX: Explainable AI for Raman Spectroscopycited by 1
  4. 2025Out-of-the-box: Black-box Causal Attacks on Object Detectorscited by 1
  5. 2026I Guess That's Why They Call it the Blues: Causal Analysis for Audio Classifierscited by 1
  6. 2025Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AIcited by 0
  7. 2026Quantifying Explainable AI-introduced signal noise on ECG data with Spectral Entropycited by 0
  8. 2026Limitations of Synthetic Data Generation in Specialized Data-Scarce Domainscited by 0
  9. 2026Generating Medical Image Counterfactuals using Causal Explanationscited by 0