Coarse-To-Fine Multiview Anomaly Coupling Network for Hyperspectral Anomaly Detection

The fundamental goal of hyperspectral anomaly detection (HAD) is the identification of pixels manifesting substantial deviations in spectral attributes when compared with their neighboring pixels. Nevertheless, the intrinsic attributes of hyperspectral images (HSIs), characterized by their high-dimensional essence and the interdependencies among spectral bands, frequently exert an influence on the efficacy of anomaly detection (AD). Furthermore, current detection algorithms often fall short in harnessing the inherent information encapsulated within HSI, thereby constraining the network's expressive potential. In response to these challenges, we introduce a multiview model tailored that amalgamates both global and local features for HAD. Specifically, the proposed method uses an unsupervised learning-based multiview network to simultaneously conduct feature analysis on both global and local attributes within HSI. The model incorporates a dual-component structure, featuring a global module using axial attention for comprehensive global attribute analysis, and a local module using a convolutional neural network (CNN) with residual connections to capture fine-grained local features. Subsequently, the global-local multiview anomaly coupling mechanism is applied to consolidate the strengths of distinct perspectives, resulting in the ultimate AD outcomes. Experimental evaluations are performed on seven public HSI datasets, demonstrating superior performance of the proposed method in comparison to other state-of-the-art approaches.