Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification
This addresses classification accuracy issues for hyperspectral image analysis, but it is incremental as it builds on existing graph-based methods by removing a specific bottleneck.
The paper tackles the problem of misclassification in semi-supervised hyperspectral image classification caused by inaccuracies in superpixel partitioning by proposing a graph-weighted contrastive learning approach that avoids superpixels and uses neural networks directly, achieving effectiveness demonstrated on three datasets.
Most existing graph-based semi-supervised hyperspectral image classification methods rely on superpixel partitioning techniques. However, they suffer from misclassification of certain pixels due to inaccuracies in superpixel boundaries, \ie, the initial inaccuracies in superpixel partitioning limit overall classification performance. In this paper, we propose a novel graph-weighted contrastive learning approach that avoids the use of superpixel partitioning and directly employs neural networks to learn hyperspectral image representation. Furthermore, while 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 to baselines relying on superpixel partitioning.