all AI news
Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding. (arXiv:2203.09175v2 [cs.CV] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Large-scale crop type classification is a task at the core of remote sensing
efforts with applications of both economic and ecological importance. Current
state-of-the-art deep learning methods are based on self-attention and use
satellite image time series (SITS) to discriminate crop types based on their
unique growth patterns. However, existing methods generalize poorly to regions
not seen during training mainly due to not being robust to temporal shifts of
the growing season caused by variations in climate. To this end, …
arxiv classification cv encoding image positional encoding satellite series time time series