mlsanityData to 14 Oct 2026

Towards Desiderata-Driven Design of Visual Counterfactual Explainers

arXiv 2506.14698 ↗First posted 17 Jun 2025cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations, such as feature attribution, by revealing the specific data transformations to which a machine learning model responds most strongly. In this paper, we argue that existing VCEs focus too narrowly on optimizing sample quality or change minimality; they fail to consider the more holistic desiderata for an explanation, such as fidelity, understandability, and sufficiency. To address this shortcoming, we explore new mechanisms for counterfactual generation and investigate how they can help fulfill these desiderata. We combine these mechanisms into a novel 'smooth counterfactual explorer' (SCE) algorithm and demonstrate its effectiveness through systematic evaluations on synthetic and real data.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 59 of its 82 references that are in the map. First posted on arXiv 17 Jun 2025.

Builds on

59 of 82 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  11. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  12. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
38 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  2. 2018Sanity Checks for Saliency Mapscited by 1,156
  3. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  5. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 647
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  7. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  8. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  9. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  10. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  11. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulationscited by 244
  12. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  13. 2018Disentangling Adversarial Robustness and Generalizationcited by 172
  14. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  15. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 157
  16. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  17. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  18. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
  19. 2022Diffusion Visual Counterfactual Explanationscited by 96
  20. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 88
  21. 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
  22. 2022Diffusion Models for Counterfactual Explanationscited by 79
  23. 2023On the Foundations of Shortcut Learningcited by 65
  24. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  25. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  26. 2023Adversarial Counterfactual Visual Explanationscited by 47
  27. 2019Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variabilitycited by 44
  28. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  29. 2021Toward Explainable AI for Regression Modelscited by 31
  30. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  31. 2022Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geosciencecited by 28
  32. 2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
  33. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  34. 2024The Clever Hans Effect in Unsupervised Learningcited by 24
  35. 2022Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanationscited by 22
  36. 2021Consequence-aware Sequential Counterfactual Generationcited by 17
  37. 2022Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAIcited by 16
  38. 2024Global Counterfactual Directionscited by 15

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamplescited by 7
  2. 2026Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Modelscited by 4
  3. 2025Imbalanced Classification through the Lens of Spurious Correlationscited by 3
  4. 2026Protein Counterfactuals via Diffusion-Guided Latent Optimizationcited by 3
  5. 2026SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation modelscited by 3
  6. 2026Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversioncited by 1
  7. 2026Towards Fast and Disentangled Counterfactuals for Visual Foundation Modelscited by 0