Importance-Aware Filter Selection for Convolutional Neural Network Acceleration

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2019 IEEE International Conference on Visual Communications and Image Processing (VCIP)
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)978-1-7281-3723-0
ISBN (Print)978-1-7281-3724-7
Publication statusPublished - Dec 2019

Publication series

NameIEEE International Conference on Visual Communications and Image Processing, VCIP
ISSN (Print)1018-8770
ISSN (Electronic)2642-9357

Conference

Title34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
LocationAerial UTS Function Centre
PlaceAustralia
CitySydney
Period1 - 4 December 2019

Abstract

Convolutional Neural Networks(CNNs) are widely used in many fields, including artificial intelligence, computer vision and video coding. However, CNNs are typically overparameterized and contain significant redundancy. Traditional model acceleration methods mainly rely on specific manual rules. This usually leads to sub-optimal results with relatively limited compression ratio. Recent works have deployed the self-learning agent on the layer-level acceleration but still combined with human-designed criterias. In this paper, we proposed a filter-based model acceleration method to directly and automatically decide which filters should be pruned with the reinforcement learning method DDPG. We designed a novel reward function with the reward shaping technique for the training process. Our method is utilized on the models trained on MNIST and CIFAR-10 datasets and achieves both higher acceleration ratio and less accuracy loss than the conventional methods simultaneously.

Research Area(s)

  • CNNs acceleration, Deep learning, Model acceleration, Reinforcement learning

Citation Format(s)

Importance-Aware Filter Selection for Convolutional Neural Network Acceleration. / Liu, Zikun; Chen, Zhen; Li, Weiping.

2019 IEEE International Conference on Visual Communications and Image Processing (VCIP). Institute of Electrical and Electronics Engineers, 2019. 8965838 (IEEE International Conference on Visual Communications and Image Processing, VCIP).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review