MetaAMC: meta learning and AutoML for model compression

Chaopeng Zhang; Yuesheng Zhu; Zhiqiang Bai

doi:10.1117/12.2573095

12 June 2020 MetaAMC: meta learning and AutoML for model compression

Chaopeng Zhang, Yuesheng Zhu, Zhiqiang Bai

Proceedings Volume 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020); 115191U (2020) https://doi.org/10.1117/12.2573095
Event: Twelfth International Conference on Digital Image Processing, 2020, Osaka, Japan

Abstract

Model compression reduces the computation costs of an over-parameterized network without performance damage, and channel pruning is among the predominant approaches to compress deep neural networks. In this paper, we propose a novel approach called MetaAMC combining meta learning and Auto ML for automatic channel pruning of very deep neural networks. It leverages meta learning and reinforcement learning to provide the model compression policy. Compared to not only the original AMC and MetaPruning but also the state-of-the-art pruning methods, we have demonstrated superior performances on MobileNet V1/V2 and ResNet-50.

Citation Download Citation

Chaopeng Zhang, Yuesheng Zhu, and Zhiqiang Bai "MetaAMC: meta learning and AutoML for model compression", Proc. SPIE 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020), 115191U (12 June 2020); https://doi.org/10.1117/12.2573095

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available