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-...

Cijeli opis

Bibliografski detalji
Glavni autori: Wei Zhang, Ping Tang, Thomas Corpetti, Lijun Zhao
Format: Članak
Jezik:English
Izdano: MDPI AG 2021-01-01
Serija:Remote Sensing
Teme:
Online pristup:https://www.mdpi.com/2072-4292/13/3/394

Slični predmeti