Publications
Detailed Information
FALCON: FAst and Lightweight CONvolution for Compressing and Accelerating Convolutional Neural Networks
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Advisor
- Kang, U
- Issue Date
- 2019-08
- Publisher
- 서울대학교 대학원
- Keywords
- CNN compression ; CNN acceleration ; convolution
- Description
- 학위논문(석사)--서울대학교 대학원 :공과대학 컴퓨터공학부,2019. 8. Kang, U.
- Abstract
- How can we efficiently compress Convolution Neural Networks (CNN) while maintaining the accuracy of classification tasks? One of the promising approaches is based on depthwise separable convolution which replaces a standard convolution with a depthwise convolution and pointwise convolution. However, previous works based on the depthwise separable convolution are limited since 1) they are mostly heuristic approaches without precise understanding of their relations to the standard convolution, and 2) their accuracies cannot match that of the standard convolution.
In this paper, we propose FALCON, an accurate and lightweight method for compressing CNN. FALCON is derived by interpreting existing convolution methods based on depthwise separable convolution using EHP, our proposed mathematical formulation to approximate the standard convolution kernel. Such interpretation leads to developing a generalized version rank-k FALCON which further improves the accuracy while sacrificing a bit of compression and computation. Experiments show that FALCON outperforms 1) existing methods based on depthwise separable convolution, and 2) the standard CNN model by up to 8× compression and 8× computation reduction while ensuring similar accuracy. We also demonstrate that rank-k FALCON provides even better accuracy than the standard convolution in many cases, while using smaller numbers of parameters and floating point operations.
- Language
- eng
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.