论文标题
一种轻巧的方法来培养（GRAD）CAM的可解释性和分类网络的解释性
A light-weight method to foster the (Grad)CAM interpretability and explainability of classification networks
论文作者
论文摘要
我们考虑了一种轻重量方法，该方法允许改善局部分类网络的解释性。该方法通过修改训练损失在训练过程中考虑（GRAD）CAM地图，并且不需要其他结构元素。已经证明，通过多个指标衡量的（GRAD）CAM可解释性可以通过这种方式进行改进。由于该方法应适用于嵌入式系统和标准更深的架构，因此在训练过程中基本上利用了二阶导数，并且不需要其他模型层。
We consider a light-weight method which allows to improve the explainability of localized classification networks. The method considers (Grad)CAM maps during the training process by modification of the training loss and does not require additional structural elements. It is demonstrated that the (Grad)CAM interpretability, as measured by several indicators, can be improved in this way. Since the method shall be applicable on embedded systems and on standard deeper architectures, it essentially takes advantage of second order derivatives during the training and does not require additional model layers.
