Improving Semantic Segmentation via Video Propagation and Label Relaxation

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks. We exploi...

Celý popis

Podrobná bibliografia

Vydané v:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 8848 - 8857
Hlavní autori:	Zhu, Yi, Sapra, Karan, Reda, Fitsum A., Shih, Kevin J., Newsam, Shawn, Tao, Andrew, Catanzaro, Bryan
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 01.06.2019
Predmet:	Annotations Cognition Computer vision Deep Learning Grouping and Shape Image and Video Synthesis Predictive models Segmentation Semantics Training Uncertainty
ISSN:	1063-6919
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!