Pearl Causal Hierarchy on Image Data: Intricacies & Challenges

TL;DR

This paper explores the application of Pearl's Causal Hierarchy to image data, highlighting the complexities and challenges faced when integrating causality theories into computer vision tasks.

Contribution

It provides a detailed analysis of how Pearl's Causal Hierarchy can be understood in the context of image data, revealing key intricacies and challenges.

Findings

Identifies specific challenges in applying Pearl's causality to image data

Provides insights into the intricacies of causal reasoning in computer vision

Highlights the need for ground truth benchmarks in causal image analysis

Abstract

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.