Semantic segmentation via highly fused convolutional network with multiple soft cost functions
Sign Up to like & getrecommendations! Published in 2019 at "Cognitive Systems Research"
DOI: 10.1016/j.cogsys.2018.04.004
Abstract: Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: feature downsampling, combined feature upsampling and multiple… read more here.
Keywords: network; segmentation; multiple soft; highly fused ... See more keywords