Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles. Inspired by the dynamic receptive field in the human being's visual system, we propose t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-05
Hauptverfasser:	Sun, Xin, Chen, Changrui, Wang, Xiaorui, Dong, Junyu, Zhou, Huiyu, Chen, Sheng
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Computer Science - Computer Vision and Pattern Recognition Convolution Image segmentation Neural networks Normal distribution
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!