mlsanityData to 7 Oct 2026

Diffeomorphic Counterfactuals with Generative Models

arXiv 2206.05075 ↗First posted 10 Jun 2022cs.LG cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic coordinate transformation and then perform gradient ascent in these coordinates to find counterfactuals which are classified with great confidence as a specified target class. We propose two methods to leverage generative models to construct such suitable coordinate systems that are either exactly or approximately diffeomorphic. We analyze the generation process theoretically using Riemannian differential geometry and validate the quality of the generated counterfactuals using various qualitative and quantitative measures.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 70 of its 119 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

70 of 119 references.

References · 70

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  2. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  10. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  11. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  12. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  13. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  14. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  15. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  16. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  17. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  18. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  19. 2021GAN Inversion: A Surveycited by 366
  20. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  21. 2019Counterfactual Visual Explanationscited by 312
  22. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  23. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  24. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  25. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  26. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  27. 2019Explanations can be manipulated and geometry is to blamecited by 215
  28. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  29. 2020Machine Learning Force Fieldscited by 204
  30. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  31. 2017Generating Natural Adversarial Examplescited by 182
  32. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  33. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  34. 2021E(n) Equivariant Normalizing Flowscited by 165
  35. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  36. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  37. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  38. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 9; 2025: 7; 2026: 10.

29 papers.

Sort:

By area:

  1. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 115
  2. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  3. 2022Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspacescited by 25
  4. 2023Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillationcited by 14
  5. 2024Probabilistically Plausible Counterfactual Explanations with Normalizing Flowscited by 11
  6. 2023Preemptively Pruning Clever-Hans Strategies in Deep Neural Networkscited by 9
  7. 2024Counterfactual Explanations via Riemannian Latent Space Traversalcited by 9
  8. 2024Symmetry Discovery for Different Data Typescited by 7
  9. 2025Towards Desiderata-Driven Design of Visual Counterfactual Explainerscited by 7
  10. 2024Generating Likely Counterfactuals Using Sum-Product Networkscited by 6
  11. 2025Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamplescited by 6
  12. 2025Diffusion Counterfactuals for Image Regressorscited by 5
17 more
  1. 2024Equivariant Neural Tangent Kernelscited by 4
  2. 2025LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matchingcited by 4
  3. 2025Graph Diffusion Counterfactual Explanationcited by 4
  4. 2026Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Modelscited by 4
  5. 2026Protein Counterfactuals via Diffusion-Guided Latent Optimizationcited by 3
  6. 2024Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAIcited by 2
  7. 2025Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Modelscited by 2
  8. 2026Counterfactual Explanations on Robust Perceptual Geodesicscited by 2
  9. 2026SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation modelscited by 2
  10. 2026Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attributioncited by 2
  11. 2026Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversioncited by 1
  12. 2024Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifoldscited by 0
  13. 2025RIE-SenseNet: Riemannian Manifold Embedding of Multi-Source Industrial Sensor Signals for Robust Pattern Recognitioncited by 0
  14. 2026Residual-Space Evolutionary Optimization via Flow-based Generative Modelscited by 0
  15. 2026Diffeomorphic Optimizationcited by 0
  16. 2026Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagationcited by 0
  17. 2026Towards Fast and Disentangled Counterfactuals for Visual Foundation Modelscited by 0