首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis
【24h】

Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis

机译:重新探测释放类别激活映射的评估:新型度量和实验分析

获取原文

摘要

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.
机译:由于对深度学习解决方案的要求增加,可解释性的需求更为根本性。 在该设置中,已经特别注意可视化技术,其尝试将与网络输出的每个输入像素归因于每个输入像素。 在本文中,我们专注于类激活映射(CAM)方法,通过取激活图的加权平均来提供有效的可视化。 为了提高这些方法的评估和再现性,我们提出了一组新颖的指标,以量化解释图,其表现出更好的有效性并简化了方法之间的比较。 为了评估提案的适当性,我们对整个想象验证集进行了不同的基于CAM的可视化方法,促进了正确的比较和再现性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号