High Fidelity Image Counterfactuals with Probabilistic Causal Models
This work addresses the problem of generating precise counterfactual images for researchers in causal inference and computer vision, representing a novel method for a known bottleneck.
The authors tackled the challenge of estimating high-fidelity image counterfactuals using a causal generative modeling framework, achieving accurate abduction and estimation of direct, indirect, and total effects as measured by axiomatic soundness.
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.