Circle-U-Net: An Efficient Architecture for Semantic Segmentation

Circle-U-Net: An Efficient Architecture for Semantic Segmentation

State-of-the-art semantic segmentation methods rely too much on complicated deep networks and thus cannot train efficiently. This paper introduces a novel Circle-U-Net architecture that exceeds the original U-Net on several standards. The proposed model includes circle connect layers, which is the b...

Full description

Bibliographic Details
Main Authors: Feng Sun, Ajith Kumar V, Guanci Yang, Ansi Zhang, Yiyun Zhang
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Algorithms
Subjects:
U-Net
deep learning
object segmentation
attention mechanism
convolutional neural network (CNN)
Online Access:https://www.mdpi.com/1999-4893/14/6/159

Internet

https://www.mdpi.com/1999-4893/14/6/159

Similar Items