Multiple Different Black Box Explanations for Image Classifiers
CoRR(2023)
摘要
Existing explanation tools for image classifiers usually give only a single
explanation for an image's classification. For many images, however, both
humans and image classifiers accept more than one explanation for the image
label. Thus, restricting the number of explanations to just one is arbitrary
and severely limits the insight into the behavior of the classifier. In this
paper, we describe an algorithm and a tool, MultiReX, for computing multiple
explanations of the output of a black-box image classifier for a given image.
Our algorithm uses a principled approach based on causal theory. We analyse its
theoretical complexity and provide experimental results showing that MultiReX
finds multiple explanations on 96
benchmark, whereas previous work finds multiple explanations only on 11
更多查看译文
关键词
multiple different explanations,image
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要