Pearl Causal Hierarchy on Image Data: Intricacies & Challenges
It addresses foundational issues in causal inference for computer vision researchers, but is primarily conceptual without new empirical results.
This paper examines how Pearl's Causal Hierarchy can be applied to image data, highlighting both insights and challenges in integrating causal concepts with computer vision.
Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems. As in any other growing subfield, patience seems to be a virtue since significant progress on integrating notions from both fields takes time, yet, major challenges such as the lack of ground truth benchmarks or a unified perspective on classical problems such as computer vision seem to hinder the momentum of the research movement. This present work exemplifies how the Pearl Causal Hierarchy (PCH) can be understood on image data by providing insights on several intricacies but also challenges that naturally arise when applying key concepts from Pearlian causality to the study of image data.