Název:	Multiscale fully convolutional denseNet for semantic segmentation
Autoři:	Brahimi, Sourour Ben Aoun, Najib Ben Amar, Chokri Benoit, Alexandre Lambert, Patrick
Citace zdrojového dokumentu:	Journal of WSCG. 2018, vol. 26, no. 2, p. 104-111.
Datum vydání:	2018
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	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)
Klíčová slova:	sémantická segmentace;konvoluční neuronová síť;plně konvoluční DenseNet;hustý blok;víceměřítková jaderná predikce
Klíčová slova v dalším jazyce:	semantic segmentation;convolutional neural network;fully convolutional DenseNet;dense block;multiscale kernel prediction
Abstrakt v dalším jazyce:	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.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	Volume 26, Number 2 (2018)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.