arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01399cs.LGcs.AI
收藏

使用概念定位图解释基于AI的决策支持系统

Explaining AI-based Decision Support Systems using Concept Localization Maps

TU Kaiserslautern(凯泽斯劳滕工业大学);German Research Center for Artificial Intelligence GmbH (DFKI)(德国人工智能研究中心)

Adriano Lucieri, Muhammad Naseer Bajwa, Andreas Dengel, Sheraz Ahmed

摘要:

基于人工智能的决策支持系统(DSS)中,使用视觉输入方式的人为中心的可解释性直接关系到这些算法的可靠性和实用性。如果一个准确而强大的决策支持系统不能为其预测提供合理的理由,它可能不会得到关键应用领域专家的信任。本文介绍了概念定位图(CLMs),这是一种新的方法对可解释的图像分类器作为决策支持系统。CLM通过在训练的图像分类器的潜在空间中定位与学习的概念相对应的显著区域来扩展概念激活向量(CAV)。它们为分类器的学习能力提供了定性和定量的保证,并专注于在图像识别过程中对人类重要的类似概念。为了更好地理解所提出的方法的有效性,我们生成了一个新的合成数据集,称为简单概念数据库(SCDB),其中包括10个可区分的概念的注释,并将其公开。我们在SCDB以及一个名为CelebA的真实数据集上评估了我们提出的方法。我们在SCDB上使用SE-ResNeXt-50对大多数相关概念实现了80%以上的本地化召回,对所有概念的平均召回率超过60%。我们在这两个数据集上的研究结果表明,CLM在实践中很有希望减轻DSS的接受程度。

英文摘要:

Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of experts in critical application areas if it is not able to provide reasonable justification of its predictions. This paper introduces Concept Localization Maps (CLMs), which is a novel approach towards explainable image classifiers employed as DSS. CLMs extend Concept Activation Vectors (CAVs) by locating significant regions corresponding to a learned concept in the latent space of a trained image classifier. They provide qualitative and quantitative assurance of a classifier's ability to learn and focus on similar concepts important for humans during image recognition. To better understand the effectiveness of the proposed method, we generated a new synthetic dataset called Simple Concept DataBase (SCDB) that includes annotations for 10 distinguishable concepts, and made it publicly available. We evaluated our proposed method on SCDB as well as a real-world dataset called CelebA. We achieved localization recall of above 80% for most relevant concepts and average recall above 60% for all concepts using SE-ResNeXt-50 on SCDB. Our results on both datasets show great promise of CLMs for easing acceptance of DSS in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑