Optical-guided neural collapse for SAR few-shot incremental learning

Arxiv CS.CV (computer vision)

Paper proposes optical-guided neural collapse to improve few-shot class incremental learning in synthetic aperture radar (SAR) imagery. The method handles SAR-specific challenges like azimuth sensitivity and data scarcity.

Arxiv CS.CV (computer vision)·Fan ZhangSijin ZhengFei MaQiang YinYongsheng ZhouFei GaoXian Sun

7 days ago