hh.sePublications
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
Deep Neural Network Compressionfor Image Classification and Object Detection
Volvo Technology AB, VGTT, Gothenburg, Sweden.
Volvo Technology AB, VGTT, Gothenburg, Sweden.
Volvo Technology AB, VGTT, Gothenburg, Sweden.
Volvo Technology AB, VGTT, Gothenburg, Sweden.
Show others and affiliations
2019 (English)Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real-time image classification or object detection. In this work, we propose a network-agnostic model compression method infused with a novel dynamical clustering approach to reduce the computational cost and memory footprint of deep neural networks. We evaluated our new compression method on five different state-of-the-art image classification and object detection networks. In classification networks, we pruned about 95% of network parameters. In advanced detection networks such as YOLOv3, our proposed compression method managed to reduce the model parameters up to 59.70% which yielded 110X less memory without sacrificing much in accuracy.

Place, publisher, year, edition, pages
2019.
National Category
Communication Systems
Identifiers
URN: urn:nbn:se:hh:diva-41097OAI: oai:DiVA.org:hh-41097DiVA, id: diva2:1375103
Conference
18th IEEE International Conference on Machine Learning and Applications (ICMLA 2019), December 16-19, Boca Raton, Florida, USA
Funder
Knowledge FoundationVinnova, 2018-05001Available from: 2019-12-04 Created: 2019-12-04 Last updated: 2019-12-11

Open Access in DiVA

No full text in DiVA

Authority records BETA

Erdal Aksoy, Eren

Search in DiVA

By author/editor
Erdal Aksoy, Eren
By organisation
CAISR - Center for Applied Intelligent Systems Research
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 16 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