Bi-Temporal Benefits: Progressive Spectral-Spatial-Temporal Feature Extraction for Hyperspectral Image Classification.

Abstract

Spectral-spatial feature extraction widely serves as the foundation for hyperspectral image classification (HSIC). However, its effectiveness decreases when applied to land covers with temporal variations. This limitation arises from lack of the temporal dimension in existing HSIC methods, hindering their ability to model real-world surface dynamics. To tackle these problems, Bi-tEmporal HyperspectrAL image classiFication network (BehalfNet) employs the dual-branch stacked architecture to process bi-temporal images, learning spectral-spatial-temporal features. Within each stacked block, features undergo the sequential feature processing pipeline. Specifically, the progressive adaptive fusion (PAF) module firstly extracts foundational spectral-spatial features for each temporal phase through long-short term fusion. These features are then refined at an intra-temporal level by the gated spectral-spatial attention (GSSA) module. Subsequently, the bi-temporal self-cross attention (BTSCA) module effectively captures the complex dynamic changes between the bi-temporal features using a novel closed-loop attention mechanism. Furthermore, the Anji dataset was introduced as the first publicly available dataset for bit-emporal HSIC. Comprehensive experiments on the Anji and public Viareggio datasets (originally used for anomaly change detection) demonstrate the competitiveness of the proposed BehalfNet over other state-of-the-art HSIC methods. The code and Anji dataset will be released at https://github.com/lixinghua5540/BehalfNet.