# Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ

arXiv: https://arxiv.org/abs/2212.08733 · HTML: https://mlsanity.com/paper/2212.08733/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 122 references that are in the map.
- First posted on arXiv 16 Dec 2022.

## Builds on (most cited first, 30 of 62)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [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)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)

## Built on by (most cited first, 12 of 12)

- [Can LLMs Explain Themselves Counterfactually?](https://mlsanity.com/paper/2502.18156/) (2025)
- [Sparse and Faithful Explanations Without Sparse Models](https://mlsanity.com/paper/2402.09702/) (2024)
- ["What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts](https://mlsanity.com/paper/2403.05652/) (2024)
- [What-If Explanations Over Time: Counterfactuals for Time Series Classification](https://mlsanity.com/paper/2603.27792/) (2026)
- [Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments](https://mlsanity.com/paper/2602.13784/) (2026)
- [Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcare](https://mlsanity.com/paper/2408.17401/) (2024)
- [Improving Decision Sparsity](https://mlsanity.com/paper/2410.20483/) (2024)
- [Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions](https://mlsanity.com/paper/2507.06029/) (2025)
- [An Information-Flow Perspective on Explainability Requirements: Specification and Verification](https://mlsanity.com/paper/2509.01479/) (2025)
- [Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations](https://mlsanity.com/paper/2604.09573/) (2026)
- [Addressing the Selection Problem in Explainable AI](https://mlsanity.com/paper/2608.22356/) (2026)
- [Diversified and Perceptible Counterfactual Examples Leveraging Expert Knowledge](https://mlsanity.com/paper/2609.15609/) (2026)

## Abstract (arXiv)

Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains and proposed legal compliance. While over 100 counterfactual methods exist, claiming to generate plausible explanations akin to those preferred by people, few have actually been tested on users (~7%). So, the psychological validity of these counterfactual algorithms for effective XAI for image data is not established. This issue is addressed here using a novel methodology that (i) gathers ground truth human-generated counterfactual explanations for misclassified images, in two user studies and, then, (ii) compares these human-generated ground-truth explanations to computationally-generated explanations for the same misclassifications. Results indicate that humans do not "minimally edit" images when generating counterfactual explanations. Instead, they make larger, "meaningful" edits that better approximate prototypes in the counterfactual class.