# Generative Counterfactual Introspection for Explainable Deep Learning

arXiv: https://arxiv.org/abs/1907.03077 · HTML: https://mlsanity.com/paper/1907.03077/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 30 of 36)

- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals](https://mlsanity.com/paper/2103.11972/) (2021)
- [Cycle-Consistent Counterfactuals by Latent Transformations](https://mlsanity.com/paper/2203.15064/) (2022)
- [Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals](https://mlsanity.com/paper/2203.12892/) (2022)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [Conditional Generative Models for Counterfactual Explanations](https://mlsanity.com/paper/2101.10123/) (2021)
- [Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning](https://mlsanity.com/paper/2106.02597/) (2021)
- [Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset](https://mlsanity.com/paper/2204.11642/) (2022)
- [MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation](https://mlsanity.com/paper/2205.15540/) (2022)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [Interpretability Guarantees with Merlin-Arthur Classifiers](https://mlsanity.com/paper/2206.00759/) (2022)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays](https://mlsanity.com/paper/2207.04394/) (2022)
- [Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network](https://mlsanity.com/paper/2110.14927/) (2021)
- [SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems](https://mlsanity.com/paper/2307.15786/) (2023)
- [LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching](https://mlsanity.com/paper/2510.14623/) (2025)
- [Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces](https://mlsanity.com/paper/2206.05257/) (2022)
- [Two-Stage Holistic and Contrastive Explanation of Image Classification](https://mlsanity.com/paper/2306.06339/) (2023)
- [Reliable Graph Neural Network Explanations Through Adversarial Training](https://mlsanity.com/paper/2106.13427/) (2021)
- [Counterfactual Explanations for Deep Learning-Based Traffic Forecasting](https://mlsanity.com/paper/2405.00456/) (2024)
- [Discriminative Attribution from Counterfactuals](https://mlsanity.com/paper/2109.13412/) (2021)
- [Explaining the Black-box Smoothly- A Counterfactual Approach](https://mlsanity.com/paper/2101.04230/) (2021)
- [Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models](https://mlsanity.com/paper/2106.01440/) (2021)
- [Explainability Requires Interactivity](https://mlsanity.com/paper/2109.07869/) (2021)
- [DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss](https://mlsanity.com/paper/2104.09062/) (2021)

## Abstract (arXiv)

In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental interventional operation that allows us to obtain answers to counterfactual inquiries, i.e., what meaningful change can be made to the input image in order to alter the prediction. We demonstrate how to reveal interesting properties of the given classifiers by utilizing the proposed introspection approach on both the MNIST and the CelebA dataset.