论文标题
基于公理的毕业-CAM：迈向CNN的准确可视化和解释
Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
论文作者
论文摘要
为了更好地理解和使用卷积神经网络（CNN），近年来，CNN的可视化和解释引起了人们的关注。特别是，已经提出了几种类激活映射（CAM）方法，以发现CNN的决策与图像区域之间的联系。尽管有合理的可视化，但缺乏明确和足够的理论支持是这些方法的主要局限性。在本文中，我们将两个公理 - 保护和灵敏度引入了CAM方法的可视化范式。同时，提出了一个专用的基于公理的GRAD-CAM（XGRAD-CAM），以尽可能满足这些公理。实验表明，就保护和灵敏度而言，Xgrad-CAM是Grad-CAM的增强版本。与Grad-CAM ++和Ablation-Cam相比，它能够获得比Grad-CAM更好的可视化性能，同时也是歧视性和易于实现的。该代码可在https://github.com/fu0511/xgrad-cam上找到。
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In particular, several Class Activation Mapping (CAM) methods have been proposed to discover the connection between CNN's decision and image regions. In spite of the reasonable visualization, lack of clear and sufficient theoretical support is the main limitation of these methods. In this paper, we introduce two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods. Meanwhile, a dedicated Axiom-based Grad-CAM (XGrad-CAM) is proposed to satisfy these axioms as much as possible. Experiments demonstrate that XGrad-CAM is an enhanced version of Grad-CAM in terms of conservation and sensitivity. It is able to achieve better visualization performance than Grad-CAM, while also be class-discriminative and easy-to-implement compared with Grad-CAM++ and Ablation-CAM. The code is available at https://github.com/Fu0511/XGrad-CAM.
