Unsupervised Cross-Domain Polarimetric Synthetic Aperture Radar (PolSAR) Change Monitoring Based on Limited-Label Transfer Learning and Vision Transformer
Limited labels and detailed changed land-cover interpretation requirements pose challenges for time-series PolSAR change monitoring research. Accurate labels and supervised models are difficult to reuse between massive unlabeled time-series PolSAR data due to the complex distribution shifts caused b...
Saved in:
| Main Authors: | Xinyue Zhang, Rong Gui, Jun Hu, Jinghui Zhang, Lihuan Tan, Xixi Zhang |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/10/1782 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Compensation for topographic effect on P-band PolSAR data with a polarimetric decomposition technique
by: Yin Zhang, et al.
Published: (2025-03-01) -
PDCNet: A Polarimetric Data-Enhanced Contrastive Learning Network for PolSAR Land Cover Classification
by: Bo Ren, et al.
Published: (2025-01-01) -
PolSAR Image Classification Framework With POA Align and Cyclic Channel Attention
by: Xiaoxiao Fang, et al.
Published: (2024-01-01) -
PolSAR-MPIformer: A Vision Transformer Based on Mixed Patch Interaction for Dual-Frequency PolSAR Image Adaptive Fusion Classification
by: Xinyue Xin, et al.
Published: (2024-01-01) -
Classification evaluation and improvement of airborne PolSAR images for land use mapping using deep learning
by: Jiafeng Wang, et al.
Published: (2024-01-01)