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
Semantic Segmentation: Using Convolutional Neural Networks and Sparse dictionaries
Linköping University, Department of Electrical Engineering, Computer Vision.
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The two main bottlenecks using deep neural networks are data dependency and training time. This thesis proposes a novel method for weight initialization of the convolutional layers in a convolutional neural network. This thesis introduces the usage of sparse dictionaries. A sparse dictionary optimized on domain specific data can be seen as a set of intelligent feature extracting filters. This thesis investigates the effect of using such filters as kernels in the convolutional layers in the neural network. How do they affect the training time and final performance?

The dataset used here is the Cityscapes-dataset which is a library of 25000 labeled road scene images.The sparse dictionary was acquired using the K-SVD method. The filters were added to two different networks whose performance was tested individually. One of the architectures is much deeper than the other. The results have been presented for both networks. The results show that filter initialization is an important aspect which should be taken into consideration while training the deep networks for semantic segmentation.

Place, publisher, year, edition, pages
2017. , p. 43
Keywords [en]
convolution neural network, sparse dictionaries, cnn, computer vision, machine learning, road scene, artificial intelligence
Keywords [sv]
neuronnät, maskininlärning, datorseende, aetificiell intelligens, cnn
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-139367ISRN: LiTH-ISY-EX--17/5054--SEOAI: oai:DiVA.org:liu-139367DiVA, id: diva2:1127291
External cooperation
Combitech
Subject / course
Electrical Engineering
Supervisors
Examiners
Available from: 2017-08-09 Created: 2017-07-13 Last updated: 2017-08-09Bibliographically approved

Open Access in DiVA

fulltext(4920 kB)197 downloads
File information
File name FULLTEXT01.pdfFile size 4920 kBChecksum SHA-512
dca8e29ed66f8a7c19cd7a24c56cccddee69e355df194aead00239e3a5f392447de5ccda1353fde2d19eb41e5102181188f0f798166a5171f4ff7460c32e63bd
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Andersson, Viktor
By organisation
Computer Vision
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 197 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1757 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