Sinusoidal Covariate Shift for Domain Generalization
收藏DataCite Commons2025-05-15 更新2025-05-17 收录
下载链接:
https://dataverse.harvard.edu/citation?persistentId=doi:10.7910/DVN/HR4YRZ
下载链接
链接失效反馈官方服务:
资源简介:
This dataset consists of 16,384 evenly spaced points over 16 periods of the sine function. Each domain corresponds to a distinct period, enabling structured covariate shift across training and test domains. Used to benchmark domain generalization.
该数据集包含正弦函数16个周期内的16,384个均匀分布点。每个域对应一个独特周期,可在训练域与测试域间实现结构化协变量偏移,用于基准测试域泛化能力。
提供机构:
Harvard Dataverse
创建时间:
2025-05-13



