Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process

Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process

Automatic building semantic segmentation is the most critical and relevant task in several geospatial applications. Methods based on convolutional neural networks (CNNs) are mainly used in current building segmentation. The requirement of huge pixel-level labels is a significant obstacle to achieve...

Full description

Bibliographic Details
Main Authors: Khaled Moghalles, Heng-Chao Li, Abdulwahab Alazeb
Format: Article
Language:English
Published: MDPI AG 2022-05-01
Series:Entropy
Subjects:
building semantic segmentation
deep learning
weakly supervised learning
very high resolution
imagery
Online Access:https://www.mdpi.com/1099-4300/24/5/741

Similar Items

Similar Items