Aligning Characteristic Descriptors with Images for Human-Expert-like Explainability

TL;DR

This paper introduces a novel explainability method for deep learning models in critical domains, using characteristic descriptors and a concept bottleneck to generate expert-like natural language explanations based on image features.

Contribution

The paper proposes a new approach that employs characteristic descriptors and a concept bottleneck layer to produce faithful, natural language explanations aligned with human expert reasoning.

Findings

Outperforms saliency map-based explanations in experiments

Provides inherently faithful and interpretable model decisions

Effective in face recognition and chest X-ray diagnosis

Abstract

In mission-critical domains such as law enforcement and medical diagnosis, the ability to explain and interpret the outputs of deep learning models is crucial for ensuring user trust and supporting informed decision-making. Despite advancements in explainability, existing methods often fall short in providing explanations that mirror the depth and clarity of those given by human experts. Such expert-level explanations are essential for the dependable application of deep learning models in law enforcement and medical contexts. Additionally, we recognize that most explanations in real-world scenarios are communicated primarily through natural language. Addressing these needs, we propose a novel approach that utilizes characteristic descriptors to explain model decisions by identifying their presence in images, thereby generating expert-like explanations. Our method incorporates a concept bottleneck layer within the model architecture, which calculates the similarity between image and descriptor encodings to deliver inherent and faithful explanations. Through experiments in face recognition and chest X-ray diagnosis, we demonstrate that our approach offers a significant contrast over existing techniques, which are often limited to the use of saliency maps. We believe our approach represents a significant step toward making deep learning systems more accountable, transparent, and trustworthy in the critical domains of face recognition and medical diagnosis.