Mutual Information Analysis in Multimodal Learning Systems

TL;DR

This paper introduces InfoMeter, a system for estimating mutual information between modalities in multimodal learning, revealing that lower mutual information can improve detection accuracy in autonomous driving systems.

Contribution

The paper presents a novel method for estimating mutual information in multimodal systems and provides new insights into how modality relationships affect task performance.

Findings

Lower mutual information correlates with higher detection accuracy.

InfoMeter effectively estimates mutual information in complex systems.

Analysis on autonomous driving data demonstrates practical utility.

Abstract

In recent years, there has been a significant increase in applications of multimodal signal processing and analysis, largely driven by the increased availability of multimodal datasets and the rapid progress in multimodal learning systems. Well-known examples include autonomous vehicles, audiovisual generative systems, vision-language systems, and so on. Such systems integrate multiple signal modalities: text, speech, images, video, LiDAR, etc., to perform various tasks. A key issue for understanding such systems is the relationship between various modalities and how it impacts task performance. In this paper, we employ the concept of mutual information (MI) to gain insight into this issue. Taking advantage of the recent progress in entropy modeling and estimation, we develop a system called InfoMeter to estimate MI between modalities in a multimodal learning system. We then apply InfoMeter to analyze a multimodal 3D object detection system over a large-scale dataset for autonomous driving. Our experiments on this system suggest that a lower MI between modalities is beneficial for detection accuracy. This new insight may facilitate improvements in the development of future multimodal learning systems.