Weakly-Supervised Domain Adaptation With Adversarial Entropy for Building Segmentation in Cross-Domain Aerial Imagery

Building segmentation is a classical and challenging task in high-resolution remote sensing imagery. This approach has achieved remarkable performance based on a fully convolutional network with adequate pixel-wise annotations. However, due to differences in sensor technology as well as appearance i...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Xuedong Yao, Yandong Wang, Yanlan Wu, Zeyu Liang
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2021-01-01
Serier:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Fag:	Adversarial learning building segmentation domain adaptation (DA) high resolution self-training
Online adgang:	https://ieeexplore.ieee.org/document/9517002/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!