High Fidelity Image Counterfactuals with Probabilistic Causal Models

Abstract

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for high-dimensional structured variables, such as images, remains a challenging task. We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models. Our experiments demonstrate that our proposed mechanisms are capable of accurate abduction and estimation of direct, indirect and total effects as measured by axiomatic soundness of counterfactuals.

Cite

Text

De Sousa Ribeiro et al. "High Fidelity Image Counterfactuals with Probabilistic Causal Models." International Conference on Machine Learning, 2023.

Markdown

[De Sousa Ribeiro et al. "High Fidelity Image Counterfactuals with Probabilistic Causal Models." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/desousaribeiro2023icml-high/)

BibTeX

@inproceedings{desousaribeiro2023icml-high,
  title     = {{High Fidelity Image Counterfactuals with Probabilistic Causal Models}},
  author    = {De Sousa Ribeiro, Fabio and Xia, Tian and Monteiro, Miguel and Pawlowski, Nick and Glocker, Ben},
  booktitle = {International Conference on Machine Learning},
  year      = {2023},
  pages     = {7390-7425},
  volume    = {202},
  url       = {https://mlanthology.org/icml/2023/desousaribeiro2023icml-high/}
}