Dilated convolutions for image classification and object localization

Yasunori Kudo, Yoshimitsu Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

Yu et al.[1] showed that dilated convolutions are very effective in dense prediction problems such as semantic segmentation. In this work, we propose a new ResNet[2] based convolutional neural network model using dilated convolutions and show that this model can achieve lower error rate for image classification than ResNet with reduction of the number of the parameters of the network by 94% and that this model has high ability to localize objects despite being trained on image-level labels. We evaluated this model on ImageNet[5] which has 50 class labels randomly selected from 1000 class labels.

Original languageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages452-455
Number of pages4
ISBN (Electronic)9784901122160
DOIs
Publication statusPublished - 2017 Jul 19
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: 2017 May 82017 May 12

Publication series

NameProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
Country/TerritoryJapan
CityNagoya
Period17/5/817/5/12

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Dilated convolutions for image classification and object localization'. Together they form a unique fingerprint.

Cite this