SFE-FN: A Shuffle Feature Enhancement-Based Fusion Network for Hyperspectral and LiDAR Classification

Abstract

Under the background of the rapid development of remote sensing technology, multi-modal remote sensing image classification has attracted great attention. Considerable research has been devoted to designing more adequate multi-modal feature-level fusion networks. However, few have noted that in the process of feature fusion, if the multi-modal heterogeneous features are quite different, direct fusion may introduce noise. This greatly affects the classification performance of the network. This letter proposes a shuffle feature enhancement-based fusion network (SFE-FN) for hyperspectral and LiDAR classification, which effectively alleviates the aforementioned problems. Specifically, first, a shuffle feature enhancement module (SFE) is proposed to achieve self-enhancement and mutual enhancement of each modal feature to preliminary reduce the feature difference. Then, a cross-layer and cross-interaction module (CLCI) is designed to further enhance the consistency of features by updating parameters across layers. Finally, the proposed shuffle feature concatenation module (SFC) and shuffle feature fusion module (SFF) are utilized to adequately merge fewer differentiated features. Experiments on Houston2013 and Trento datasets show that the proposed method is effective.