Title: | Multiscale fully convolutional denseNet for semantic segmentation |
Authors: | Brahimi, Sourour Ben Aoun, Najib Ben Amar, Chokri Benoit, Alexandre Lambert, Patrick |
Citation: | Journal of WSCG. 2018, vol. 26, no. 2, p. 104-111. |
Issue Date: | 2018 |
Publisher: | Václav Skala - UNION Agency |
Document type: | článek article |
URI: | wscg.zcu.cz/WSCG2018/!_2018_Journal_WSCG-No-2.pdf http://hdl.handle.net/11025/34596 |
ISSN: | 1213-6972 (print) 1213-6980 (CD-ROM) 1213-6964 (on-line) |
Keywords: | sémantická segmentace;konvoluční neuronová síť;plně konvoluční DenseNet;hustý blok;víceměřítková jaderná predikce |
Keywords in different language: | semantic segmentation;convolutional neural network;fully convolutional DenseNet;dense block;multiscale kernel prediction |
Abstract in different language: | In the computer vision field, semantic segmentation represents a very interesting task. Convolutional Neural Network methods have shown their great performances in comparison with other semantic segmentation methods. In this paper, we propose a multiscale fully convolutional DenseNet approach for semantic segmentation. Our approach is based on the successful fully convolutional DenseNet method. It is reinforced by integrating a multiscale kernel prediction after the last dense block which performs model averaging over different spatial scales and provides more flexibility of our network to presume more information. Experiments on two semantic segmentation benchmarks: CamVid and Cityscapes have shown the effectiveness of our approach which has outperformed many recent works. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | Volume 26, Number 2 (2018) |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/34596
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.