Hyperspectral and LiDAR Data Land-Use Classification Using Parallel Transformers
Yuxuan Hu, Hao He, Lubin Weng
Abstract
It has been proved that the fusion of hyperspectral and Li-DAR data can effectively improve the performance of land-use classification. Most recent models have novel architectures which treat hyperspectral and LiDAR data equally and convolutional neural networks are widely used for extracting features of hyperspectral data. We argue that we should pay more attention to hyperspectral data and improve feature extraction tools. This paper proposes a simple yet effective model with parallel transformers. Transformers are powerful in feature extraction and feature fusion. One transformer acts as a hyperspectral image feature extractor, while the other transformer is responsible for capturing cross-modal interactions. Experiments on Houston dataset and MUUFL Gulfport dataset demonstrate that the proposed model has significantly better performance than other state-of-the-art models.