Graph-weighted contrastive learning for semi-supervised hyperspectral image classification

Le résumé fourni par la source

Most existing graph-based semi-supervised hyperspectral image (HSI) classification methods rely on superpixel partitioning techniques. However, they suffer from misclassification of certain pixels due to inaccuracies in superpixel boundaries, i.e., the initial inaccuracies in superpixel partitioning limit overall classification performance. We propose a graph-weighted contrastive learning approach that avoids the use of superpixel partitioning and directly employs neural networks to learn HSI representation. Furthermore, although many approaches require all graph nodes to be available during training, our approach supports mini-batch training by processing only a subset of nodes at a time, reducing computational complexity, and improving generalization to unseen nodes. Experimental results on three widely used datasets demonstrate the effectiveness of the proposed approach compared with baselines relying on superpixel partitioning.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.