Best learned models : Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features

Best learned models (Gaussian Processes, Random Forest, Multilayer Perceptron and Lightweight Temporal Self-Attention models) for each region based on the classification data set DS-A with seed 0 (see description here). 

Models: GP non spatial, GP spatial (sum), GP spatial (product),RF non spatial, RF spatial, MLP non spatial, MLP spatial, LTAE non spatial, LTAE spatial

For further details see section VI-C of the pre-print article "Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features ". This article is available here.

The implementation of the models is available in the open source repository.