AdGAP: Advanced Global Average Pooling

Authors

  • Arna Ghosh McGill University
  • Biswarup Bhattacharya University of Southern California
  • Somnath Basu Roy Chowdhury Indian Institute of Technology Kharagpur

Keywords:

Global average pooling, Convolutional neural networks, MNIST, Feature maps, Class activation maps

Abstract

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.

Downloads

Published

2018-04-29

How to Cite

Ghosh, A., Bhattacharya, B., & Basu Roy Chowdhury, S. (2018). AdGAP: Advanced Global Average Pooling. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12154