FSS-1000
收藏arXiv2025-09-30 收录
下载链接:
https://github.com/hkustcv/fss-1000
下载链接
链接失效反馈官方服务:
资源简介:
该数据集名为FSS-1000,包含了1000个类别,这些类别被划分为520个用于训练、240个用于验证以及240个用于测试。其规模达到了1000个类别,任务专注于少样本语义分割。
This dataset, named FSS-1000, comprises 1000 categories, which are divided into three subsets: 520 for training, 240 for validation, and 240 for testing. It is dedicated to few-shot semantic segmentation tasks.



