Generalized Zero-Shot Domain Adaptation for Unsupervised Cross-Domain PolSAR Image Classification

Cross-domain polarimetric synthetic aperture radar interpretation is urgently needed, due to the rapid data growth and label scarcity. However, the class distribution shift problems hinder the reuse of labeled samples among cross-domain images. Most of the existing domain adaptations can only handle...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Rong Gui, Xin Xu, Rui Yang, Kailiang Deng, Jun Hu
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2022-01-01
Saila:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Gaiak:	Generalized zero-shot learning (GZSL) polarimetric synthetic aperture radar (PolSAR) image scattering component semantics (SCS) stacked autoencoder (SAE) unsupervised domain adaptation (uDA)
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/9647973/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!