Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation
基于损失对齐的木本植被砍伐检测用于零样本再生与木部分割
机构 * New South Wales Department of Climate Change, Energy, the Environment and Water(新南威尔士州气候变化、能源、环境与水利部) ; Monash University(莫纳什大学) ; University of New England(新英格兰大学) ; University of Newcastle(纽卡斯尔大学)
专题命中 其他图像生成 :image generation(abstract);分类 cs.CV
AI总结 本研究提出带损失缩放系数α的双时相Sentinel-2影像木本植被变化检测模型,经影像增强与生成技术实现零样本迁移,木部分割误差降18.2%,木本植被再生F1达0.845
Comments Published in IEEE Transactions on Geoscience and Remote Sensing