Towards Causal Physical Error Discovery in Video Analytics Systems

TL;DR

This paper proposes using causal reasoning, specifically regression discontinuity design, to improve explanations of video analytics systems by linking model behavior to real-world physical phenomena, enhancing debugging and interpretability.

Contribution

It introduces a novel approach that integrates causal reasoning into video analytics explanations, connecting system metrics to physical events for better interpretability.

Findings

Conceptual framework for causal explanations in video analytics

Potential to improve debugging and system understanding

System architecture overview and future impact discussion

Abstract

Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug. Current model explanation system are very good at giving literal explanations of behavior in terms of pixel contributions but cannot integrate information about the physical or systems processes that might influence a prediction. This paper introduces the idea that a simple form of causal reasoning, called a regression discontinuity design, can be used to associate changes in multiple key performance indicators to physical real world phenomena to give users a more actionable set of video analytics explanations. We overview the system architecture and describe a vision of the impact that such a system might have.