Increasing demands for understanding the internal behavior of convolutional neural networks (CNNs) have led to remarkable improvements in explanation methods. Particularly, several class activation mapping (CAM) based methods, which generate visual explanation maps by a linear combination of activation maps from CNNs, have been proposed. However, the majority of the methods lack a clear theoretical basis on how they assign the coefficients of the linear combination. In this paper, we revisit the intrinsic linearity of CAM with respect to the activation maps; we construct an explanation model of CNN as a linear function of binary variables that denote the existence of the corresponding activation maps. With this approach, the explanation model can be determined by additive feature attribution methods in an analytic manner. We then demonstrate the adequacy of SHAP values, which is a unique solution for the explanation model with a set of desirable properties, as the coefficients of CAM. Since the exact SHAP values are unattainable, we introduce an efficient approximation method, LIFT-CAM, based on DeepLIFT. Our proposed LIFT-CAM can estimate the SHAP values of the activation maps with high speed and accuracy. Furthermore, it greatly outperforms other previous CAM-based methods in both qualitative and quantitative aspects.

翻译：对理解进化神经网络内部行为的需求不断增加,这导致解释方法的显著改进。特别是,提出了几种基于阶级激活绘图(CAM)的方法,这些方法通过CNN激活地图的线性组合产生直线解释图;然而,大多数方法缺乏关于如何分配线性组合系数的明确理论基础。在本文件中,我们重新审视CAM与激活地图的内在线性关系;我们构建了CNN的解释模型,作为显示相应启动地图存在的二进制变量的线性功能。采用这种方法,解释模型可以以分析方式由添加性特征归属方法确定。然后,我们展示了SHAP值的充分性,这是解释模型的独特解决办法,其中含有一套理想属性的系数,作为CAM的系数。由于精确的SHAP值是无法实现的,我们采用了一种高效的近似法,即以DeepLIFT为基础的LI-CAM。我们提议的LFT-CAM可以以高速度和准确度的方式对启动的地图的SHAP值进行估算。此外,我们提议的LIFT-CAM能够以高速度和高质量方面的方式对其他SMA。