DPGUNet: A Dynamic Pyramidal Graph U-Net for SAR Image Classification
Kang Ni, Chunyang Yuan, Zhizhong Zheng, Nan Tian Huang, Peng Wang · IEEE Transactions on Aerospace and Electronic Systems · 2024
Benefiting from the inherent capability of graph convolutional neural networks (GCNs) to flexibly convolve over regions with arbitrary shapes, they could model the spatial topology of SAR land covers. However, existing GCNs-based classification methods often work on a static graph and perform graph average pooling which have the fixed weights as a node pooling style, thus lacking the dynamic graph pooling representation of SAR patches under complex spatial structure. Moreover, distinguishable feature learning under different GCN blocks is generally ignored, resulting in GCNs-based methods struggling to exploit intrinsic topological structure of SAR land covers across all scales. To alleviate these issues, we propose a Dynamic Pyramidal Graph U-Net (DPGUNet), including residual graph convolution modulate fusion layer (RGCMF), attentional node feature aggregation pooling layer (ANFAP), and graph pyramidal feature learning module (GPFL), for leveraging spatial topological structures and hierarchical semantic features of SAR patches effectively. To be specific, RGCMF performs SAR global and local feature fusion between the pre-activation graph convolution and its residual branch via graph attention feature fusion module (GAFF); ANFAP is employed to transfer node information between dynamic graphs in pooling stage; Furthermore, we utilize a GPFL, which is defined by cross-scale merging association matrices, to acquire multi-scale spatial topological and contextual semantic features of SAR patches. Experimental results on three real SAR land cover classification datasets demonstrate the superiority of DPGUNet compared to several other related methods. Code is available athttps://github.com/RSIP-NJUPT/DPGUNet.