SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion

SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion

The lack of pixel-level labeling limits the practicality of deep learning-based building semantic segmentation. Weakly supervised semantic segmentation based on image-level labeling results in incomplete object regions and missing boundary information. This paper proposes a weakly supervised semanti...

Full description

Bibliographic Details
Main Authors: Jie Chen, Fen He, Yi Zhang, Geng Sun, Min Deng
Format: Article
Language:English
Published: MDPI AG 2020-03-01
Series:Remote Sensing
Subjects:
building detection
weakly supervised learning
superpixel
semantic segmentation
deep learning
Online Access:https://www.mdpi.com/2072-4292/12/6/1049

Internet

https://www.mdpi.com/2072-4292/12/6/1049

Similar Items