论文标题
IS-CAM：基于公理的解释的集成得分板
IS-CAM: Integrated Score-CAM for axiomatic-based explanations
论文作者
论文摘要
卷积神经网络被称为黑盒模型，因为人类无法解释其内部功能。为了使CNN更容易解释和值得信赖，我们提出了IS-CAM（Integrated Score-CAM），在此，我们在Score-CAM管道中介绍了集成操作，以实现视觉上的更加清晰的属性映射。我们的方法对来自ILSVRC 2012验证数据集的2000个随机选择的图像进行了评估，该图像证明了IS-CAM的多功能性以说明不同的模型和方法。
Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustworthy, we propose IS-CAM (Integrated Score-CAM), where we introduce the integration operation within the Score-CAM pipeline to achieve visually sharper attribution maps quantitatively. Our method is evaluated on 2000 randomly selected images from the ILSVRC 2012 Validation dataset, which proves the versatility of IS-CAM to account for different models and methods.
