Hyperspectral Image Classification via Multiscale Multiangle Attention Network

Hyperspectral images (HSIs) provide a large amount of spatial and spectral information to characterize ground objects. However, they also contain a lot of redundant information, which makes it difficult to extract complex local and global spatial–spectral features. Considering that HSIs present multiscale similarity and anisotropic image features, multiscale and multiangle information can be used to effectively model local and global features and reduce the complexity of self-attention. This article proposes a new multiscale multiangle attention network (MMAN) for HSI classification that models the internal relationship between image features at local and global scales. First, three spectral–spatial feature extraction modules (at different scales) are constructed to extract the low-level features of the image. These modules are first used by a 3-D convolutional layer for spectral feature extraction and then input to a 2-D convolutional layer for spatial feature extraction. Next, the serialized tokens are input to the multiangle attention module. Finally, the learnable labels are identified through a linear layer, and the features of different scales are fused through a fully connected layer to realize the classification of samples. Experimental results on four standard datasets show that the proposed exhibits comparable or superior classification performance than other state-of-the-art methods.