Hierarchical Shrinkage Multi-Scale Network for Hyperspectral Image Classification with Hierarchical Feature Fusion

Hongmin Gao, Zhonghao Chen, Chenming Li
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Recently, deep learning (DL) based hyperspectral image classification (HSIC) has attracted substantial attention. Many works based on the convolutional neural network (CNN) model have been certificated to be significantly successful for boosting the performance of HSIC. However, most of these methods extract features by using a fixed convolutional kernel and ignore multi-scale features of the ground objects of hyperspectral images (HSIs). Although some recent methods have proposed multi-scale
more » ... ature extraction schemes, more computing and storage resources were consumed. Moreover, when using CNN to implement hyperspectral image classification, many methods only use the high-level semantic information extracted from the end of the network, ignoring the edge information extracted from shallow layers of the network. To settle the preceding two issues, a novel HSIC method based on hierarchical shrinkage multi-scale network (HSMSN) and the hierarchical feature fusion (HFF) is proposed, with which the newly proposed classification framework can fuse features generated by both of multi-scale receptive field and multiple levels. Specifically, multi-depth and multi-scale residual block (MDMSRB) is constructed by superposition dilated convolution to realize multi-scale feature extraction. Furthermore, according to the change of feature size in different stages of the neural networks, we design a hierarchical shrinkage multi-scale feature extraction network by pruning MDMSRB to reduce the redundancy of network structure. In addition, to make full use of the features extracted in each stage of the network, the proposed network hierarchically integrates low-level edge features and high-level semantic features effectively. Experimental results demonstrate that the proposed method achieves more competitive performance with a limited computational cost than other state-of-the-art methods. Index Terms-Hyperspectral image classification (HSIC), convolutional neural network (CNN), hierarchical shrinkage multi-scale network (HSMSN), multi-depth and multi-scale residual block (MDMSRB), hierarchical feature fusion (HFF)
doi:10.1109/jstars.2021.3083283 fatcat:vgnfuwahxvganblzrjjabmtwc4