The Ability of Image-Language Explainable Models to Resemble Domain Expertise

TL;DR

This paper investigates how image-language models can generate explanations resembling domain expertise using local surrogate techniques, aiming to improve transparency and guidance in healthcare applications.

Contribution

It introduces a method combining local surrogate explainability with vision-language models to produce domain-resembling explanations in healthcare.

Findings

Explanations help guide model training for data scientists.

Local surrogates can produce multi-modal visual and language explanations.

The approach enhances model transparency and domain relevance.

Abstract

Recent advances in vision and language (V+L) models have a promising impact in the healthcare field. However, such models struggle to explain how and why a particular decision was made. In addition, model transparency and involvement of domain expertise are critical success factors for machine learning models to make an entrance into the field. In this work, we study the use of the local surrogate explainability technique to overcome the problem of black-box deep learning models. We explore the feasibility of resembling domain expertise using the local surrogates in combination with an underlying V+L to generate multi-modal visual and language explanations. We demonstrate that such explanations can serve as helpful feedback in guiding model training for data scientists and machine learning engineers in the field.