Bottom-Up Scattering Information Perception Network for SAR target recognition
This work addresses performance bottlenecks and poor robustness in SAR target recognition for applications like remote sensing, though it appears incremental as it builds on existing deep learning methods with novel components.
The paper tackled the problem of insufficient perception and mining of scattering information in SAR image target recognition by proposing a bottom-up scattering information perception network, which improved interpretability and discriminative ability, achieving validated performance on the FAST-Vehicle and SAR-ACD datasets.
Deep learning methods based synthetic aperture radar (SAR) image target recognition tasks have been widely studied currently. The existing deep methods are insufficient to perceive and mine the scattering information of SAR images, resulting in performance bottlenecks and poor robustness of the algorithms. To this end, this paper proposes a novel bottom-up scattering information perception network for more interpretable target recognition by constructing the proprietary interpretation network for SAR images. Firstly, the localized scattering perceptron is proposed to replace the backbone feature extractor based on CNN networks to deeply mine the underlying scattering information of the target. Then, an unsupervised scattering part feature extraction model is proposed to robustly characterize the target scattering part information and provide fine-grained target representation. Finally, by aggregating the knowledge of target parts to form the complete target description, the interpretability and discriminative ability of the model is improved. We perform experiments on the FAST-Vehicle dataset and the SAR-ACD dataset to validate the performance of the proposed method.