Awesome

WHUS2-CD+

WHUS2-CD+ is a cloud validation detection dataset for Sentinel-2A images. WHUS2-CD+ contains 36 manually labeled cloud masks at 10m resolution and corresponding Sentinel-2A images evenly distributed over China mainland. WHUS2-CD+ can be downloaded on: https://pan.baidu.com/s/1ien7Oi-5TEm_3Nrd1lBIzg Extraction code: s2cd.
Or on: https://doi.org/10.5281/zenodo.5511792.

The environmental dependencies are listed in CDFM3SF.yml. Researchers can re-produce the training and testing dataset by running Autoprocess.py (just replace the sorcedir in all .py file). The reported results in ref 1 are CDFM3SF-mask.rar, CDFM3SF-10-mask.rar and CDFM3SF-4-mask.rar, respectively. (0, 128 and 255 are for nodata, clear and cloud pixels, respectively)

Distributions of 36 images of the WHUS2-CD+ dataset. Land cover types credit: ESA-CCI-LC (Defourny et al., 2017).

If you use this dataset for your research, please cite us accordingly:
J. Li, Z. Wu, Z. Hu, C. Jian, S. Luo, L. Mou, X. Zhu, and M. Molinier, "A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features," in IEEE Transactions on Geoscience and Remote Sensing, 2021, doi: https://doi.org/10.1109/TGRS.2021.3069641.
Z. Wu, J. Li, Y. Wang, Z. Hu and M. Molinier, "Self-Attentive Generative Adversarial Network for Cloud Detection in High Resolution Remote Sensing Images," in IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 10, pp. 1792-1796, Oct. 2020, doi: https://doi.org/10.1109/LGRS.2019.2955071.