Fine-Grained Pixel-Wise Hyperspectral Land-Cover Classification in Large-Scale Scenes Using Patch-Based Hypergraph Feature Enrichment

Research summary

A parallel 3D-CNN and Mamba encoder reads each raw hyperspectral patch. Hypergraph feature enrichment connects information across scales to improve fine-class recognition in large scenes.

Approach and contribution

An alignment and fusion gate brings local boundary cues together with long-range context. A hypergraph built from training-patch embeddings enriches decoder skips. Evaluated on Matiwan and Qingpu using region-based splits and sliding-window inference.

Read the original work

Find on Google Scholar

This page summarises the public publication record. The original paper defines the method, evaluation protocol and scope of its findings.