arXiv:2306.15764cs.LG
High Fidelity Image Counterfactuals with Probabilistic Causal Models
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
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.
Ever wondered how we can make our deep generative models respect causal structure? This is key to creating authentic "what if" scenarios in our images! In our latest research, we deal with high-fidelity image counterfactuals, the generation of images based on "what if" scenarios…
slothofgalaxyView on HNParent context