# Explaining Visual Models by Causal Attribution

arXiv: https://arxiv.org/abs/1909.08891 · HTML: https://mlsanity.com/paper/1909.08891/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 18 of 18)

- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries](https://mlsanity.com/paper/2110.14690/) (2021)
- [Deep Structural Causal Shape Models](https://mlsanity.com/paper/2208.10950/) (2022)
- [Deep Causal Learning: Representation, Discovery and Inference](https://mlsanity.com/paper/2211.03374/) (2022)
- [Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation](https://mlsanity.com/paper/2109.04518/) (2021)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference](https://mlsanity.com/paper/2509.20211/) (2025)
- [Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces](https://mlsanity.com/paper/2206.05257/) (2022)
- [Causal Generative Explainers using Counterfactual Inference: A Case Study on the Morpho-MNIST Dataset](https://mlsanity.com/paper/2401.11394/) (2024)
- [Counterfactual Explanations for Deep Learning-Based Traffic Forecasting](https://mlsanity.com/paper/2405.00456/) (2024)
- [Causal Feature Selection for Responsible Machine Learning](https://mlsanity.com/paper/2402.02696/) (2024)
- [Explanatory causal effects for model agnostic explanations](https://mlsanity.com/paper/2206.11529/) (2022)
- [Provable Robust Saliency-based Explanations](https://mlsanity.com/paper/2212.14106/) (2022)
- [CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals](https://mlsanity.com/paper/2602.15546/) (2026)
- [Causality-Aware Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2212.05256/) (2022)
- [A Framework for Causal Concept-based Model Explanations](https://mlsanity.com/paper/2512.02735/) (2025)

## Abstract (arXiv)

Model explanations based on pure observational data cannot compute the effects of features reliably, due to their inability to estimate how each factor alteration could affect the rest. We argue that explanations should be based on the causal model of the data and the derived intervened causal models, that represent the data distribution subject to interventions. With these models, we can compute counterfactuals, new samples that will inform us how the model reacts to feature changes on our input. We propose a novel explanation methodology based on Causal Counterfactuals and identify the limitations of current Image Generative Models in their application to counterfactual creation.