mlsanityData to 14 Oct 2026

Explanation by Progressive Exaggeration

arXiv 1911.00483 ↗First posted 1 Nov 2019cs.LG cs.AI cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance (e.g. saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually changes the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 16; 2023: 14; 2024: 12; 2025: 7; 2026: 5.

76 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  2. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  3. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  4. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  5. 2022Diffusion Models for Counterfactual Explanationscited by 79
  6. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  7. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  8. 2023Adversarial Counterfactual Visual Explanationscited by 47
  9. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  10. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  11. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  12. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
38 more
  1. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  2. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  3. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  4. 2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
  5. 2021Robust Feature-Level Adversaries are Interpretability Toolscited by 27
  6. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  7. 2021Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimatescited by 19
  8. 2021CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanationscited by 17
  9. 2025PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusioncited by 17
  10. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 16
  11. 2023Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?cited by 16
  12. 2021Designing Counterfactual Generators using Deep Model Inversioncited by 15
  13. 2024Global Counterfactual Directionscited by 15
  14. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  15. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14
  16. 2022Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Datasetcited by 13
  17. 2022Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differcited by 12
  18. 2021Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbationcited by 11
  19. 2023Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactualscited by 10
  20. 2023Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeatcited by 10
  21. 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
  22. 2024Counterfactual Explanations via Riemannian Latent Space Traversalcited by 9
  23. 2023Integrating Earth Observation Data into Causal Inference: Challenges and Opportunitiescited by 8
  24. 2023On the Impact of Knowledge Distillation for Model Interpretabilitycited by 8
  25. 2021On Quantitative Evaluations of Counterfactualscited by 7
  26. 2022Diagnostics for Deep Neural Networks with Automated Copy/Paste Attackscited by 6
  27. 2023Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluationcited by 6
  28. 2021Using Causal Analysis for Conceptual Deep Learning Explanationcited by 5
  29. 2021Neural-to-Tree Policy Distillation with Policy Improvement Criterioncited by 5
  30. 2021Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Networkcited by 5
  31. 2022Towards a More Rigorous Science of Blindspot Discovery in Image Classification Modelscited by 5
  32. 2024The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanationscited by 5
  33. 2025LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matchingcited by 5
  34. 2022When less is more: Simplifying inputs aids neural network understandingcited by 4
  35. 2022Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africacited by 4
  36. 2023Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classificationcited by 4
  37. 2024Unsupervised Model Diagnosiscited by 4
  38. 2022A Rigorous Study Of The Deep Taylor Decompositioncited by 3

50 most cited of 76 All 76 (JSON)