Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability

TL;DR

This paper introduces a self-explainable deep learning system for image classification that not only predicts classes but also explains its decisions and detects potential errors, enhancing safety in critical applications.

Contribution

The paper presents a novel SE-DL system that generates human-understandable explanations and leverages them for effective error detection in image classifiers.

Findings

The SE-DL system improves error detection accuracy.

Concept selection enhances error detection performance.

Compared schemes outperform non-explainable error detection methods.

Abstract

This paper proposes a self-explainable Deep Learning (SE-DL) system for an image classification problem that performs self-error detection. The self-error detection is key to improving the DL system's safe operation, especially in safety-critical applications such as automotive systems. A SE-DL system outputs both the class prediction and an explanation for that prediction, which provides insight into how the system makes its predictions for humans. Additionally, we leverage the explanation of the proposed SE-DL system to detect potential class prediction errors of the system. The proposed SE-DL system uses a set of concepts to generate the explanation. The concepts are human-understandable lower-level image features in each input image relevant to the higher-level class of that image. We present a concept selection methodology for scoring all concepts and selecting a subset of them based on their contribution to the error detection performance of the proposed SE-DL system. Finally, we present different error detection schemes using the proposed SE-DL system to compare them against an error detection scheme without any SE-DL system.