Grad-CAM: Why did you say that?

RR Selvaraju, A Das, R Vedantam, M Cogswell… - arXiv preprint arXiv …, 2016 - arxiv.org
We propose a technique for making Convolutional Neural Network (CNN)-based models
more transparent by visualizing input regions that are'important'for predictions--or visual …
被引用次数：669 相关文章

Grad-CAM: Why did you say that?

RR Selvaraju, A Das, R Vedantam… - arXiv e …, 2016 - ui.adsabs.harvard.edu
We propose a technique for making Convolutional Neural Network (CNN)-based models
more transparent by visualizing input regions that are'important'for predictions--or visual …