# Sparse Visual Counterfactual Explanations in Image Space

arXiv: https://arxiv.org/abs/2205.07972 · HTML: https://mlsanity.com/paper/2205.07972/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 72 references that are in the map.
- First posted on arXiv 16 May 2022.

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [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)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [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)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [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)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Unlabeled Data Improves Adversarial Robustness](https://mlsanity.com/paper/1905.13736/) (2019)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](https://mlsanity.com/paper/2010.03593/) (2020)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)

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

- [Diffusion Visual Counterfactual Explanations](https://mlsanity.com/paper/2210.11841/) (2022)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Latent Diffusion Counterfactual Explanations](https://mlsanity.com/paper/2310.06668/) (2023)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://mlsanity.com/paper/2410.12591/) (2024)
- [DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations](https://mlsanity.com/paper/2311.17833/) (2023)
- [Emerging Synergies in Causality and Deep Generative Models: A Survey](https://mlsanity.com/paper/2301.12351/) (2023)
- [Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics](https://mlsanity.com/paper/2502.11725/) (2025)
- [Discriminative Class Tokens for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17155/) (2023)
- [Deep Backtracking Counterfactuals for Causally Compliant Explanations](https://mlsanity.com/paper/2310.07665/) (2023)
- [Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation](https://mlsanity.com/paper/2308.06100/) (2023)
- [Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion](https://mlsanity.com/paper/2312.13616/) (2023)
- [Sparse and Faithful Explanations Without Sparse Models](https://mlsanity.com/paper/2402.09702/) (2024)
- [Feature Accentuation: Revealing 'What' Features Respond to in Natural Images](https://mlsanity.com/paper/2402.10039/) (2024)
- [CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations](https://mlsanity.com/paper/2406.01649/) (2024)
- [From Visual Explanations to Counterfactual Explanations with Latent Diffusion](https://mlsanity.com/paper/2504.09202/) (2025)
- [Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models](https://mlsanity.com/paper/2311.11629/) (2023)
- [Robustness in Both Domains: CLIP Needs a Robust Text Encoder](https://mlsanity.com/paper/2506.03355/) (2025)
- [Do Counterfactual Examples Complicate Adversarial Training?](https://mlsanity.com/paper/2404.10588/) (2024)
- [Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation](https://mlsanity.com/paper/2510.13872/) (2025)
- [Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations](https://mlsanity.com/paper/2511.20295/) (2025)
- [Which Modality Decides? Counterfactual Modality Attribution for Multimodal LLMs](https://mlsanity.com/paper/2608.00076/) (2026)
- [When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images](https://mlsanity.com/paper/2608.23024/) (2026)
- [Clarity: an improved gradient method for producing quality visual counterfactual explanations](https://mlsanity.com/paper/2211.15370/) (2022)
- [Improving Decision Sparsity](https://mlsanity.com/paper/2410.20483/) (2024)
- [SafeFix: Targeted Model Repair via Controlled Image Generation](https://mlsanity.com/paper/2508.08701/) (2025)
- [Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks](https://mlsanity.com/paper/2602.06578/) (2026)
- [FiRe: Fixed-Noise Refinement for Visual Counterfactual Explanations](https://mlsanity.com/paper/2608.08664/) (2026)
- [Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model](https://mlsanity.com/paper/2609.37638/) (2026)

## Abstract (arXiv)

Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decision of the classifier would change. Their generation in image space is challenging and requires robust models due to the problem of adversarial examples. Existing techniques to generate VCEs in image space suffer from spurious changes in the background. Our novel perturbation model for VCEs together with its efficient optimization via our novel Auto-Frank-Wolfe scheme yields sparse VCEs which lead to subtle changes specific for the target class. Moreover, we show that VCEs can be used to detect undesired behavior of ImageNet classifiers due to spurious features in the ImageNet dataset.