Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Compact ConvNets with Ternary Weights and Binary Activations
KTH, School of Electrical Engineering and Computer Science (EECS), Robotics, Perception and Learning, RPL.ORCID iD: 0000-0002-4266-6746
2018 (English)Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

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 32kB 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.

Place, publisher, year, edition, pages
Plague, 2018.
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-250567OAI: oai:DiVA.org:kth-250567DiVA, id: diva2:1308078
Conference
The 23rd Computer Vision Winter Workshop
Note

QC 20190624

Available from: 2019-04-30 Created: 2019-04-30 Last updated: 2019-06-24Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

http://cmp.felk.cvut.cz/cvww2018/papers/18.pdf

Authority records BETA

Maki, Atsuto

Search in DiVA

By author/editor
Maki, Atsuto
By organisation
Robotics, Perception and Learning, RPL
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 61 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf