From heatmaps to structured explanations of image classifiers

Abstract This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained. The paper starts with describing the explainable neural network (XNN), which attempts to extract and visualize several...

詳細記述

書誌詳細

出版年:	Applied AI Letters
主要な著者:	Li Fuxin, Zhongang Qi, Saeed Khorram, Vivswan Shitole, Prasad Tadepalli, Minsuk Kahng, Alan Fern
フォーマット:	論文
言語:	英語
出版事項:	Wiley 2021-12-01
主題:	explanation of deep networks global explanations heatmap visualizations structured explanations
オンライン･アクセス:	https://doi.org/10.1002/ail2.46