Demystify squeeze networks and go beyond

Ruiyuan Lin; Yuhang Xu; Hamza Ghani; Muhan Li; C.-C. Jay Kuo

doi:10.1117/12.2567544

21 August 2020 Demystify squeeze networks and go beyond

Ruiyuan Lin, Yuhang Xu, Hamza Ghani, Muhan Li, C.-C. Jay Kuo

Proceedings Volume 11510, Applications of Digital Image Processing XLIII; 115100O (2020) https://doi.org/10.1117/12.2567544
Event: SPIE Optical Engineering + Applications, 2020, Online Only

Abstract

Small neural networks (NNs) that have a small model size find applications in mobile and wearable computing. One famous example is the SqueezeNet that achieves the same accuracy as the AlexNet yet has 50x fewer parameters than AlexNet. A few follow-ups and architectural variants have been inspired. They were built upon ad hoc arguments and experimentally justified. It remains a mystery why the SqueezeNet works efficiently. In this work, we attempt to provide a scientific explanation to the superior performance of the SqueezeNet. The function of the fire module, which is a key component of the SqueezeNet, is analyzed in detail. We study the evolution of cross-entropy values across layers and use visualization tools to shed light on its behavior with several illustrative examples.

Conference Presentation

Citation Download Citation

Ruiyuan Lin, Yuhang Xu, Hamza Ghani, Muhan Li, and C.-C. Jay Kuo "Demystify squeeze networks and go beyond", Proc. SPIE 11510, Applications of Digital Image Processing XLIII, 115100O (21 August 2020); https://doi.org/10.1117/12.2567544

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