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-...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Wei Zhang, Ping Tang, Thomas Corpetti, Lijun Zhao
Materialtyp: Artikel
Språk:English
Publicerad: MDPI AG 2021-01-01
Serie:Remote Sensing
Ämnen:
land cover classification
convolutional neural network
segmentation model
weakly supervised
seeded region growing
fully connected Conditional Random Fields
Länkar:https://www.mdpi.com/2072-4292/13/3/394

Internet

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

Liknande verk