AdGAP: Advanced Global Average Pooling

2018-02-08

Proceedings of the AAAI Conference on Artificial Intelligence, 32

Volume

Thirty-Second AAAI Conference on Artificial Intelligence 2018

Student Abstract Track

Global average pooling (GAP) has been used previously to generate class activation maps. The motivation behind AdGAP comes from the fact that the convolutional filters possess position information of the essential features and hence, combination of the feature maps could help us locate the class instances in an image. Our novel architecture generates promising results and unlike previous methods, the architecture is not sensitive to the size of the input image, thus promising wider application.

10.1609/aaai.v32i1.12154