Portal de Periódicos da CAPES

A hierarchical receptive network oriented to target recognition in SAR images

2022; Elsevier BV; Volume: 126; Linguagem: Inglês

10.1016/j.patcog.2022.108558

1873-5142

Ganggang Dong, Hongwei Liu,

Geophysical Methods and Applications

The recent years have witnessed a resurgence on neural network. Many functional layers are stacked hierarchically to learn the high-level representations. Yet the large album of radar image with label information are scarce. The fitting power of deep architectures are therefore limited. Additionally, the coherent imaging mechanism inevitably produce many speckles. They are with the statistical specificity of multiplicative noise, and hence make the image interpretation difficult. To solve the problems, this paper presents a new hierarchical receptive neural network. A signal-wise receptive module is first built by a family of delicate convolutional filters, with which the empirical features and knowledge are encoded. The receptive features are further refined in a patch-wise receptive unit, where some convolutional blocks are configured sequentially. The refined representations are finally used to make the inference. Multiple comparative studies are performed to demonstrate the advantage of proposed strategy.