OverSegNet: A convolutional encoder–decoder network for image over-segmentation

Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which ar...

Celý popis

Podrobná bibliografia

Vydané v:	Computers & electrical engineering Ročník 107; s. 108610
Hlavní autori:	Li, Peng, Ma, Wei
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.04.2023
Predmet:	Encoder–decoder architecture Image over-segmentation NAS encoder Non-iterative deep clustering Superpixel segmentation Non-iterative deep clustering Image over-segmentation Encoder–decoder architecture Superpixel segmentation NAS encoder
ISSN:	0045-7906, 1879-0755
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!