mlsanityData to 7 Oct 2026

Explaining Image Classifiers by Counterfactual Generation

arXiv 1807.08024 ↗First posted 20 Jul 2018cs.CVcited by 144

Not on the map. Why?

Abstract (arXiv)

When an image classifier makes a prediction, which parts of the image are relevant and why? We can rephrase this question to ask: which parts of the image, if they were not seen by the classifier, would most change its decision? Producing an answer requires marginalizing over images that could have been seen but weren't. We can sample plausible image in-fills by conditioning a generative model on the rest of the image. We then optimize to find the image regions that most change the classifier's decision after in-fill. Our approach contrasts with ad-hoc in-filling approaches, such as blurring or injecting noise, which generate inputs far from the data distribution, and ignore informative relationships between different parts of the image. Our method produces more compact and relevant saliency maps, with fewer artifacts compared to previous methods.

Key facts. Cited by 144 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 35; 2023: 22; 2024: 24; 2025: 12; 2026: 13.

144 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  3. 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformerscited by 116
  4. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  5. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  6. 2022Diffusion Visual Counterfactual Explanationscited by 96
  7. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 86
  8. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  9. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  10. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  11. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  12. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
38 more
  1. 2022Missingness Bias in Model Debuggingcited by 36
  2. 2023Exposing and Mitigating Spurious Correlations for Cross-Modal Retrievalcited by 35
  3. 2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
  4. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  5. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  6. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  7. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  8. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  9. 2021Temporal Dependencies in Feature Importance for Time Series Predictionscited by 27
  10. 2021ECINN: Efficient Counterfactuals from Invertible Neural Networkscited by 26
  11. 2021Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysiscited by 25
  12. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  13. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  14. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  15. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  16. 2022Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Valuecited by 23
  17. 2022Unit Testing for Concepts in Neural Networkscited by 23
  18. 2021On Causally Disentangled Representationscited by 22
  19. 2021Robust Models Are More Interpretable Because Attributions Look Normalcited by 21
  20. 2024Optimal ablation for interpretabilitycited by 21
  21. 2022Towards Counterfactual Image Manipulation via CLIPcited by 19
  22. 2021DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applicationscited by 18
  23. 2022Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detectioncited by 18
  24. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  25. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  26. 2021Designing Counterfactual Generators using Deep Model Inversioncited by 15
  27. 2021Cartoon Explanations of Image Classifierscited by 15
  28. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  29. 2022Core Risk Minimization using Salient ImageNetcited by 15
  30. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 15
  31. 2021XAI Handbook: Towards a Unified Framework for Explainable AIcited by 14
  32. 2021Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Modelcited by 14
  33. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14
  34. 2022Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Datasetcited by 13
  35. 2024Listenable Maps for Audio Classifierscited by 13
  36. 2021Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretationcited by 12
  37. 2021Resisting Out-of-Distribution Data Problem in Perturbation of XAIcited by 12
  38. 2022What You See is What You Classify: Black Box Attributionscited by 12

50 most cited of 144 All 144 (JSON)