Extending Class Activation Mapping Using Gaussian Receptive Field
This work addresses visualization for deep learning practitioners, but it is incremental as it builds directly on CAM.
The paper tackled the problem of visualizing deep learning models by improving Class Activation Mapping (CAM) through Gaussian upsampling and mathematical corrections, resulting in Extended-CAM, which provides more accurate visualization than existing methods.
This paper addresses the visualization task of deep learning models. To improve Class Activation Mapping (CAM) based visualization method, we offer two options. First, we propose Gaussian upsampling, an improved upsampling method that can reflect the characteristics of deep learning models. Second, we identify and modify unnatural terms in the mathematical derivation of the existing CAM studies. Based on two options, we propose Extended-CAM, an advanced CAM-based visualization method, which exhibits improved theoretical properties. Experimental results show that Extended-CAM provides more accurate visualization than the existing methods.