Authors:
Yanbo Feng
;
Adel Hafiane
and
Hélène Laurent
Affiliation:
INSA CVL, Laboratoire PRISME, Bourges, France
Keyword(s):
Feature Map, Convolutional Neural Network, Weakly Supervised Learning, Image Processing, Histopathological Image.
Abstract:
Feature map is obtained from the middle layer of convolutional neural network (CNN), it carries the regional information captured by network itself about the target of input image. This property is widely used in weakly supervised learning to achieve target localization and segmentation. However, the traditional method of processing feature map is often associated with the weight of output layer. In this paper, the weak correlation between feature map and weight is discussed. We believe that it is not accurate to directly transplant the weights of output layer to feature maps, the reason is that the global mean value of feature map loses its spatial information, weighting scalars cannot accurately constrain the three-dimensional feature maps. We highlight that the feature map in a specific channel has invariance to target’s location, it can stably activate the more complete region directly related to target, that is, the feature map ability has strong correlation with the channel.