Compressing Deep Networks Using Fisher Score of Feature Maps

Conference Paper

In this paper, we propose a new structural technique for pruning deep neural networks with skip-connections. Our approach is based on measuring the importance of feature maps in predicting the output of the model using their Fisher scores. These scores subsequently used for removing the less informative layers from the graph of the network. Extensive experiments on the classification of CIFAR-10, CIFAR-100, and SVHN data sets demonstrate the efficacy of our compressing method both in the number of parameters and operations.

Full Text

Duke Authors

Cited Authors

  • Soltani, M; Wu, S; Li, Y; Ravier, R; Ding, J; Tarokh, V

Published Date

  • March 1, 2021

Published In

Volume / Issue

  • 2021-March /

Start / End Page

  • 371 -

International Standard Serial Number (ISSN)

  • 1068-0314

International Standard Book Number 13 (ISBN-13)

  • 9780738112275

Digital Object Identifier (DOI)

  • 10.1109/DCC50243.2021.00083

Citation Source

  • Scopus