Multiscale Fully Convolutional DenseNet for Semantic Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Multiscale Fully Convolutional DenseNet for Semantic Segmentation

Résumé

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.
Fichier principal
Vignette du fichier
wscg_SourourBrahimi_FinalVersion.pdf (2.38 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01786688 , version 1 (06-05-2018)

Identifiants

  • HAL Id : hal-01786688 , version 1

Citer

Sourour Brahimi, Najib Ben Aoun, Chokri Ben Amar, A Benoit, Patrick Lambert. Multiscale Fully Convolutional DenseNet for Semantic Segmentation. WSCG 2018, International Conference on Computer Graphics, Visualization and Computer Vision, May 2018, Pilsen, Czech Republic. ⟨hal-01786688⟩
304 Consultations
1223 Téléchargements

Partager

Gmail Facebook X LinkedIn More