论文标题
使用概念本地化图来解释基于AI的决策支持系统
Explaining AI-based Decision Support Systems using Concept Localization Maps
论文作者
论文摘要
使用视觉输入方式对基于人工智能的决策支持系统（DSS）的解释性直接与此类算法的可靠性和实用性有关。如果它无法为其预测提供合理的理由，那么原本准确，强大的DSS可能不会享受关键应用领域的专家的信任。本文介绍了概念本地图（CLM），这是一种用于DSS的可解释图像分类器的新方法。 CLM通过在训练有素的图像分类器的潜在空间中找到对应于学习的概念的重要区域来扩展概念激活向量（CAVS）。它们为分类者学习和专注于图像识别过程中对人类重要的类似概念的能力提供了定性和定量的保证。为了更好地理解所提出方法的有效性，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个可区分概念的注释，并公开可用。我们评估了我们在SCDB上提出的方法，以及一个名为Celeba的现实数据集。对于大多数相关概念，我们实现了以上80％的本地化召回，使用SCDB上的SE-Resnext-50的所有概念平均召回率高于60％。我们在两个数据集上的结果均显示出CLM在实践中放松DSS接受的巨大希望。
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.
