# Diffusion Visual Counterfactual Explanations

arXiv: https://arxiv.org/abs/2210.11841 · HTML: https://mlsanity.com/paper/2210.11841/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 67 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Builds on (most cited first, 30 of 46)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)

## Built on by (most cited first, 30 of 96)

- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Efficient and Scalable Graph Generation through Iterative Local Expansion](https://mlsanity.com/paper/2312.11529/) (2023)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach](https://mlsanity.com/paper/2309.07944/) (2023)
- [Learning Data Representations with Joint Diffusion Models](https://mlsanity.com/paper/2301.13622/) (2023)
- [From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling](https://mlsanity.com/paper/2310.11011/) (2023)
- [Counterfactual Image Editing](https://mlsanity.com/paper/2403.09683/) (2024)
- [Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach](https://mlsanity.com/paper/2401.15652/) (2024)
- [Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models](https://mlsanity.com/paper/2404.17735/) (2024)
- [Latent Diffusion Counterfactual Explanations](https://mlsanity.com/paper/2310.06668/) (2023)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [DreaMR: Diffusion-driven Counterfactual Explanation for Functional MRI](https://mlsanity.com/paper/2307.09547/) (2023)
- [SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2308.02154/) (2023)
- [Robust image representations with counterfactual contrastive learning](https://mlsanity.com/paper/2409.10365/) (2024)
- [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://mlsanity.com/paper/2410.12591/) (2024)
- [Natural Example-Based Explainability: a Survey](https://mlsanity.com/paper/2309.03234/) (2023)
- [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://mlsanity.com/paper/2311.17833/) (2023)
- [Counterfactual contrastive learning: robust representations via causal image synthesis](https://mlsanity.com/paper/2403.09605/) (2024)
- [Probabilistically Plausible Counterfactual Explanations with Normalizing Flows](https://mlsanity.com/paper/2405.17640/) (2024)
- [Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model](https://mlsanity.com/paper/2407.17193/) (2024)
- [Emerging Synergies in Causality and Deep Generative Models: A Survey](https://mlsanity.com/paper/2301.12351/) (2023)
- [Diffusion Counterfactual Generation with Semantic Abduction](https://mlsanity.com/paper/2506.07883/) (2025)
- [Discriminative Class Tokens for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17155/) (2023)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery](https://mlsanity.com/paper/2404.10356/) (2024)
- [SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies](https://mlsanity.com/paper/2404.18326/) (2024)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [Interval Abstractions for Robust Counterfactual Explanations](https://mlsanity.com/paper/2404.13736/) (2024)

## Abstract (arXiv)

Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are 'small' but 'realistic' semantic changes of the image changing the classifier decision. Current approaches for the generation of VCEs are restricted to adversarially robust models and often contain non-realistic artefacts, or are limited to image classification problems with few classes. In this paper, we overcome this by generating Diffusion Visual Counterfactual Explanations (DVCEs) for arbitrary ImageNet classifiers via a diffusion process. Two modifications to the diffusion process are key for our DVCEs: first, an adaptive parameterization, whose hyperparameters generalize across images and models, together with distance regularization and late start of the diffusion process, allow us to generate images with minimal semantic changes to the original ones but different classification. Second, our cone regularization via an adversarially robust model ensures that the diffusion process does not converge to trivial non-semantic changes, but instead produces realistic images of the target class which achieve high confidence by the classifier.