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

Source: [Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability](<https://www.sota2.com/research/paper/68fa6dc21e209131cea3be32>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:55.899Z

Authors: Mohammad Mahdi Karimi, Azin Heidarshenas, William W. Edmonson

Published: 2022-10-15T06:50:57.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.08210>)

[PDF](<https://arxiv.org/pdf/2210.08210.pdf>)
