mlsanityData to 7 Oct 2026

High Fidelity Image Counterfactuals with Probabilistic Causal Models

arXiv 2306.15764 ↗First posted 27 Jun 2023cs.LG stat.MEcited by 53

Not on the map. Why?

Abstract (arXiv)

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 64 of its 96 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

64 of 96 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022Generative Adversarial Networkscited by 5,603
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
38 more
  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2014Conditional Generative Adversarial Netscited by 2,152
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  4. 2021Variational Diffusion Modelscited by 1,145
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  7. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  8. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  10. 2018Disentangling by Factorisingcited by 614
  11. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  12. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  13. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  14. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  15. 2015Importance Weighted Autoencoderscited by 454
  16. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  17. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
  18. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  19. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  20. 2021GAN Inversion: A Surveycited by 366
  21. 2016Ladder Variational Autoencoderscited by 315
  22. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  23. 2013Direct and Indirect Effectscited by 276
  24. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  25. 2019Causality for Machine Learningcited by 242
  26. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  27. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  28. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  29. 2021Towards Causal Representation Learningcited by 207
  30. 2019Causality matters in medical imagingcited by 193
  31. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  32. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  33. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  34. 2019Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Modelscited by 114
  35. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  36. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  37. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  38. 2022Deep End-to-end Causal Inferencecited by 93

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 17; 2025: 21; 2026: 10.

53 papers.

Sort:

By area:

  1. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  2. 2024Benchmarking Counterfactual Image Generationcited by 22
  3. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  4. 2024Counterfactual Image Editingcited by 20
  5. 2025PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusioncited by 17
  6. 2024Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessmentcited by 13
  7. 2024Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesiscited by 13
  8. 2024Mitigating attribute amplification in counterfactual image generationcited by 12
  9. 2024Robust image representations with counterfactual contrastive learningcited by 12
  10. 2023No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imagingcited by 11
  11. 2024Counterfactual contrastive learning: robust representations via causal image synthesiscited by 11
  12. 2024Counterfactual Generative Modeling with Variational Causal Inferencecited by 10
38 more
  1. 2025CF-Seg: Counterfactuals meet Segmentationcited by 10
  2. 2024Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inferencecited by 9
  3. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 8
  4. 2024Latent Causal Modeling for 3D Brain MRI Counterfactualscited by 7
  5. 2024Semi-Supervised Learning for Deep Causal Generative Modelscited by 6
  6. 2025Causally Steered Diffusion for Automated Video Counterfactual Generationcited by 5
  7. 2025Counterfactual Identifiability via Dynamic Optimal Transportcited by 5
  8. 2024Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimandcited by 4
  9. 2024Synthetic Data for Robust Stroke Segmentationcited by 4
  10. 2025Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generationcited by 4
  11. 2026Overcoming Statistical Bias in Action-Controllable World Modelscited by 4
  12. 2024MACAW: A Causal Generative Model for Medical Imagingcited by 3
  13. 2025Flow Stochastic Segmentation Networkscited by 3
  14. 2023SSL Framework for Causal Inconsistency between Structures and Representationscited by 2
  15. 2025Causal Disentanglement for Robust Long-tail Medical Image Generationcited by 2
  16. 2025Evaluation of 3D Counterfactual Brain MRI Generationcited by 2
  17. 2025Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesiscited by 2
  18. 2025Probabilistic Modelling is Sufficient for Causal Inferencecited by 2
  19. 2026Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformerscited by 2
  20. 2025Explaining 3D Computed Tomography Classifiers with Counterfactualscited by 1
  21. 2025Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imagingcited by 1
  22. 2025Integrating Anatomical Priors into a Causal Diffusion Modelcited by 1
  23. 2025GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomescited by 1
  24. 2025Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoderscited by 1
  25. 2026Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentationcited by 1
  26. 2026Generating Chest X-Ray Counterfactuals by Specialising Foundation Image Modelscited by 1
  27. 2023Reconstruction of Patient-Specific Confounders in AI-based Radiologic Image Interpretation using Generative Pretrainingcited by 0
  28. 2024Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasetscited by 0
  29. 2024Natural Counterfactuals With Necessary Backtrackingcited by 0
  30. 2024Causally Consistent Normalizing Flowcited by 0
  31. 2025Learning Counterfactual Outcomes Under Rank Preservationcited by 0
  32. 2025Unsupervised Structural-Counterfactual Generation under Domain Shiftcited by 0
  33. 2025Learning to Harmonize Cross-vendor X-ray Images by Non-linear Image Dynamics Correctioncited by 0
  34. 2025Estimating Treatment Effects with Independent Component Analysiscited by 0
  35. 2025Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulationcited by 0
  36. 2026FlexCausal: Flexible Causal Disentanglement via Structural Flow Priors and Manifold-Aware Interventionscited by 0
  37. 2026Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesiscited by 0
  38. 2026Counterfactual Stress Testing for Image Classification Modelscited by 0

50 most cited of 53 All 53 (JSON)