LAENet: Light-weight asymmetric encoder-decoder network for semantic segmentation

Encode-decoder structure is used in deep learning for real-time dense segmentation task. On account of the limitation of calculation burden on mobile devices, we present a light-weight asymmetric encoder-decoder network in this paper, namely LAENet, which quickly and efficiently accomplish the task...

Celý popis

Podrobná bibliografia

Vydané v:	Journal of physics. Conference series Ročník 1966; číslo 1; s. 12047 - 12053
Hlavní autori:	Hong, Liangyi, Duan, Shukai, Wang, Lidan, Pan, Yongbin
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Bristol IOP Publishing 01.07.2021
Predmet:	Asymmetry Coders Convolution Deep learning Electronic devices Encoders-Decoders Post-production processing Real time Semantic segmentation Semantics Weight reduction
ISSN:	1742-6588, 1742-6596
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!