MultiSpecies Canopy Segmentation: Interactive Machine-Learning and Pseudo-Labelling are key
Charles Rongione, Abraham George Smith, Céline Chevalier, Christophe De Vleeschouwer, Guillaume Lobet, Xavier Draye
This paper develops a method to train deep-learning models for multi-species canopy segmentation using FCNNs and pseudo-labeling, achieving high accuracy with reduced human effort.
bioRxiv · Dec 10, 2025 · PreprintBioengineering