Heuristic approaches for porting deep neural networks onto mobile devices

Christos Grecos; Mukul Shirvaikar; Nasser Kehtarnavaz

doi:10.1117/12.2580047

12 April 2021 Heuristic approaches for porting deep neural networks onto mobile devices

Christos Grecos, Mukul Shirvaikar, Nasser Kehtarnavaz

Proceedings Volume 11736, Real-Time Image Processing and Deep Learning 2021; 1173602 (2021) https://doi.org/10.1117/12.2580047
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Deep Neural Networks (DNNs) although promising for image processing, have significant computational complexity. This impedes implementation in resource-constrained systems. This paper presents effective heuristic approaches for porting DNNs onto mobile devices. Four sets of heuristics are studied: (1) heuristics based on the reuse of transferred weight matrices and weight pruning; (2) heuristics based on parameter reduction, network acceleration and non-tensor layer improvements; (3) a suite of heuristics for low power acceleration of DNNs based on dataflow, near memory and in-memory processing, transform schemes and analog based approaches; and (4) heuristics based on feature and feature map pruning utilizing cosine distances. These sets of heuristics achieve significant complexity, memory and power reductions with minimal reduction of accuracy across an assortment of state-of-the-art DNNs and applications.

Conference Presentation

Citation Download Citation

Christos Grecos, Mukul Shirvaikar, and Nasser Kehtarnavaz "Heuristic approaches for porting deep neural networks onto mobile devices", Proc. SPIE 11736, Real-Time Image Processing and Deep Learning 2021, 1173602 (12 April 2021); https://doi.org/10.1117/12.2580047

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