Extending Class Activation Mapping Using Gaussian Receptive Field

01/15/2020
by   Bum Jun Kim, et al.
17

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset