期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
卷 -, 期 -, 页码 2299-2304出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPRW53098.2021.00260
关键词
-
This paper focuses on Class Activation Mapping (CAM) approaches, which offer effective visualization by taking weighted averages of activation maps. It introduces a novel set of metrics to quantify explanation maps, enhancing evaluation and reproducibility. By comparing different CAM-based visualization methods on the entire ImageNet validation set, proper comparisons and reproducibility are promoted.
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据