Learning Deep Features for Discriminative Localization

← Back to document page

c as the class activation map for class c, where each spatial element is given by M c(x,y)= X k wc k f k(x,y). (2) Thus, S c = P x,y M c(x,y), and hence M c(x,y)directly indicates the importance of the activation at spatial grid (x,y)leading to the classification of an image to class c. Intuitively,basedonpriorworks[34,30],weexpecteach

  Class