mlsanityData to 7 Oct 2026

Diffusion Models for Counterfactual Explanations

arXiv 2203.15636 ↗First posted 29 Mar 2022cs.CV cs.LGcited by 79

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent diffusion models. By leveraging the guided generative diffusion process, our proposed methodology shows how to use the gradients of the target classifier to generate counterfactual explanations of input instances. Further, we analyze current approaches to evaluate spurious correlations and extend the evaluation measurements by proposing a new metric: Correlation Difference. Our experimental validations show that the proposed algorithm surpasses previous State-of-the-Art results on 5 out of 6 metrics on CelebA.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 66 of its 78 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

66 of 78 references.

Closest ancestors · 9

Same direction, newest first

  1. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  2. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  3. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  4. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  5. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  6. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  8. 2020Denoising Diffusion Implicit Models6 Oct
  9. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  9. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  10. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  11. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  12. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
38 more
  1. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  2. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  3. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  4. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  5. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  7. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  10. 2019Counterfactual Visual Explanationscited by 312
  11. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  12. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  13. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  14. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  15. 2020Neural Prototype Trees for Interpretable Fine-grained Image Recognitioncited by 213
  16. 2017Generating Natural Adversarial Examplescited by 182
  17. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  18. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  19. 2017Interpretable Convolutional Neural Networkscited by 161
  20. 2016Generating Visual Explanationscited by 156
  21. 2021Counterfactual Generative Networkscited by 111
  22. 2019Explanation by Progressive Exaggerationcited by 76
  23. 2020Interpretable and Accurate Fine-grained Recognition via Region Groupingcited by 75
  24. 2020Black-box Explanation of Object Detectors via Saliency Mapscited by 74
  25. 2020On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learningcited by 60
  26. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  27. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  28. 2020SCOUT: Self-aware Discriminant Counterfactual Explanationscited by 52
  29. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  30. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  31. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
  32. 2019Generative Counterfactual Introspection for Explainable Deep Learningcited by 36
  33. 2021A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Conceptscited by 33
  34. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  35. 2020CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Netscited by 29
  36. 2021Conditional Generative Models for Counterfactual Explanationscited by 28
  37. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  38. 2021ECINN: Efficient Counterfactuals from Invertible Neural Networkscited by 26

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 17; 2024: 18; 2025: 22; 2026: 20.

79 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,008
  2. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  3. 2023Adversarial Counterfactual Visual Explanationscited by 47
  4. 2023LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Imagescited by 46
  5. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  6. 2023Stochastic Segmentation with Conditional Categorical Diffusion Modelscited by 38
  7. 2023Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generationcited by 35
  8. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  9. 2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
  10. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  11. 2023Latent Diffusion Counterfactual Explanationscited by 17
  12. 2024Global Counterfactual Directionscited by 15
38 more
  1. 2023DreaMR: Diffusion-driven Counterfactual Explanation for Functional MRIcited by 14
  2. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14
  3. 2024Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessmentcited by 13
  4. 2024Gumbel Counterfactual Generation From Language Modelscited by 13
  5. 2024Probabilistically Plausible Counterfactual Explanations with Normalizing Flowscited by 11
  6. 2023Emerging Synergies in Causality and Deep Generative Models: A Surveycited by 10
  7. 2024Counterfactual Explanations via Riemannian Latent Space Traversalcited by 9
  8. 2024Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discoverycited by 8
  9. 2024SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policiescited by 8
  10. 2024Contrast Sets for Evaluating Language-Guided Robot Policiescited by 7
  11. 2025Towards Desiderata-Driven Design of Visual Counterfactual Explainerscited by 7
  12. 2023Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluationcited by 6
  13. 2024DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanationscited by 6
  14. 2025Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamplescited by 6
  15. 2023SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systemscited by 5
  16. 2023Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusioncited by 5
  17. 2024What could go wrong? Discovering and describing failure modes in computer visioncited by 5
  18. 2024The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanationscited by 5
  19. 2025Diffusion Counterfactuals for Image Regressorscited by 5
  20. 2025Causally Steered Diffusion for Automated Video Counterfactual Generationcited by 5
  21. 2025Guidance Watermarking for Diffusion Modelscited by 5
  22. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  23. 2024CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanationscited by 4
  24. 2024Unsupervised Model Diagnosiscited by 4
  25. 2025From Visual Explanations to Counterfactual Explanations with Latent Diffusioncited by 4
  26. 2026Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Modelscited by 4
  27. 2023Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Modelscited by 3
  28. 2025Graph Counterfactual Explainable AI via Latent Space Traversalcited by 3
  29. 2025V-CECE: Visual Counterfactual Explanations via Conceptual Editscited by 3
  30. 2026Protein Counterfactuals via Diffusion-Guided Latent Optimizationcited by 3
  31. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  32. 2024Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAIcited by 2
  33. 2024GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifierscited by 2
  34. 2025Faithful Counterfactual Visual Explanations (FCVE)cited by 2
  35. 2025Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification modelscited by 2
  36. 2026Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributionscited by 2
  37. 2026MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanationscited by 2
  38. 2026SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation modelscited by 2

50 most cited of 79 All 79 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering
  2. 2026Generating Medical Image Counterfactuals using Causal Explanations
  3. 2025DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification
  4. 2025Graph Diffusion Counterfactual Explanation
  5. 2024Ablation Based Counterfactuals
  6. 2026Rare Concept Generation via Counterfactual Inference in Diffusion Models
  7. 2024Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models
  8. 2025LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching