Scene Segmentation with DAG-Recurrent Neural Networks

In this paper, we address the challenging task of scene segmentation. In order to capture the rich contextual dependencies over image regions, we propose Directed Acyclic Graph-Recurrent Neural Networks (DAG-RNN) to perform context aggregation over locally connected feature maps. More specifically,...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2018-06, Vol.40 (6), p.1480-1493
Hauptverfasser:	Shuai, Bing, Zuo, Zhen, Wang, Bing, Wang, Gang
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks CNN COCO stuff Context context aggregation Context modeling convolutional neural networks DAG-recurrent neural networks DAG-RNN Electronic devices Embedded systems Feature extraction Feature maps Image segmentation Neural networks Object segmentation pascal context Recurrent neural networks Scene segmentation Semantics sift flow Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!