Compact ConvNets with Ternary Weights and Binary Activations

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F18%3A00318883" target="_blank" >RIV/68407700:21730/18:00318883 - isvavai.cz</a>

Result on the web

<a href="http://cmp.felk.cvut.cz/cvww2018/papers/18.pdf" target="_blank" >http://cmp.felk.cvut.cz/cvww2018/papers/18.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Compact ConvNets with Ternary Weights and Binary Activations

Original language description

Compact convolutional neural network (CNN) architectures with ternary weights and binary activations is a combination of methods suitable for making neural networks more efficient. We show that the combination of ternary weights and depthwise separable convolutions on the CIFAR-10 benchmark can yield a small neural network of size $32 kB$ and $83.70%$ test accuracy. We present a novel dithering binary activation which we expected to improve accuracy of networks with binary activations by randomizing quantization error. This work presents the outcome of our experiments which show that it brings only mild improvements. A compact SqueezeNet network with ternary weights and binary activations is more accurate than the same network with binary weights. Nevertheless, the accuracy gap to its full precision variant remains large.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/EF15_003%2F0000470" target="_blank" >EF15_003/0000470: Robotics 4 Industry 4.0</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 23rd Computer Vision Winter Workshop

ISBN

978-80-270-3395-9

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

—

Publisher name

Czech Society for Cybernetics and Informatics

Place of publication

Praha

Event location

Český Krumlov

Event date

Feb 5, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—