A particular class of Explainable AI (XAI) methods provide saliency maps to
highlight part of the image a Convolutional Neural Network (CNN) model looks at
to classify the image as a way to explain its working. These methods provide an
intuitive way for users to understand predictions made by CNNs. Other than
quantitative computational tests, the vast majority of evidence to highlight
that the methods are valuable is anecdotal. Given that humans would be the
end-users of such methods, we devise three human subject experiments through
which we gauge the effectiveness of these saliency-based explainability
methods.

本文结合三个人体实验研究基于显著性的可解释性方法对于卷积神经网络的解释效果，并评估其可行性。

基于显著性的可解释性方法评估

Evaluation of Saliency-based Explainability Method

The human visual system can spot an abnormal image, and reason about what
makes it strange. This task has not received enough attention in computer
vision. In this paper we study various types of atypicalities in images in a
more comprehensive way than has been done before. We propose a new dataset of
abnormal images showing a wide range of atypicalities. We design human subject
experiments to discover a coarse taxonomy of the reasons for abnormality. Our
experiments reveal three major categories of abnormality: object-centric,
scene-centric, and contextual. Based on this taxonomy, we propose a
comprehensive computational model that can predict all different types of
abnormality in images and outperform prior arts in abnormality recognition.

本文研究了在计算机视觉中，如何利用人类视觉系统对图像异常性进行识别和分类，提出了一种基于人类实验数据的异常图像分类法以及一种能够准确预测各种异常情况的计算模型，并相应建立了一个异常图像数据集。