WTS: A Weakly towards Strongly Supervised Learning Framework for Remote Sensing Land Cover Classification Using Segmentation Models

WTS: A Weakly towards Strongly Supervised Learning Framework for Remote Sensing Land Cover Classification Using Segmentation Models

Land cover classification is one of the most fundamental tasks in the field of remote sensing. In recent years, fully supervised fully convolutional network (FCN)-based semantic segmentation models have achieved state-of-the-art performance in the semantic segmentation task. However, creating pixel-...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Wei Zhang, Ping Tang, Thomas Corpetti, Lijun Zhao
Materyal Türü: Makale
Dil:English
Baskı/Yayın Bilgisi: MDPI AG 2021-01-01
Seri Bilgileri:Remote Sensing
Konular:
land cover classification
convolutional neural network
segmentation model
weakly supervised
seeded region growing
fully connected Conditional Random Fields
Online Erişim:https://www.mdpi.com/2072-4292/13/3/394

Internet

https://www.mdpi.com/2072-4292/13/3/394

Benzer Materyaller