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.
翻译:本文为进行自我检测的图像分类问题提出了一个可自我解释的深学习(SE-DL)系统。自我检测是改进DL系统安全操作的关键,特别是在汽车系统等安全关键应用程序中。SE-DL系统输出了等级预测和该预测的解释,从而可以洞察到系统如何对人类作出预测。此外,我们利用拟议的SE-DL系统的解释来探测系统潜在的等级预测错误。提议的SE-DL系统使用一套概念来产生解释。这些概念是每张与该图像较高等级有关的输入图像中人类无法理解的低层次图像特征。我们提出了一个概念选择方法,根据所有概念的评分和根据它们对拟议的SE-DL系统错误检测性能的贡献选择其中的一组。最后,我们提出了不同的错误探测方案,利用提议的SE-DL系统来比较它们与没有SE-DL系统的错误检测计划。