@article{nguyen_vatsavai_2025, title={Foundation Models for Semantic Segmentation of Thick/Thin Clouds and Cloud-shadows: A Comparative Study}, url={https://doi.org/10.1145/3748636.3762766}, DOI={10.1145/3748636.3762766}, abstractNote={Clouds pose the most significant hindrance to satellite imagery analysis. A crucial step in pre-processing satellite imagery involves masking these clouds, which ensures reliable downstream geospatial analysis. However, this masking also reduces the effectively analyzed region. To address this, recent studies have explored imputing missing values under clouds to restore a complete image. Unfortunately, the inaccuracy of the off-the-shelf masks (e.g., QA band from Landsat 8) adversely affects downstream geospatial analysis and machine learning tasks. Accurate imputation necessitates precise detection of clouds, including thin clouds and shadows. Of recent cloud segmentation models segmenting a subset of the cloud phenomena (i.e., thick clouds, thin clouds, and cloud-shadows), their accuracy, though promising, remains insufficient; even fewer models segment all three phenomena with adequate performance. Foundational models show promise for image segmentation tasks, but studies with them in cloud segmentation are sparse. In this paper, we present a thorough experimental analysis, studying different properties of foundational model and their effectiveness on this comprehensive task at different levels of transfer learning. This analysis will explore foundational model architecture, pretraining dataset, and scheme. The main result we found is the transformer architecture demonstrates superior performance on granular details on boundaries and small-sized segments, compared to convolutional or hybrid architectures.}, author={Nguyen, Calvin and Vatsavai, Ranga Raju}, year={2025}, month={Nov} }