S
Shunjun Wei
Researcher at University of Electronic Science and Technology of China
Publications - 166
Citations - 2016
Shunjun Wei is an academic researcher from University of Electronic Science and Technology of China. The author has contributed to research in topics: Synthetic aperture radar & Computer science. The author has an hindex of 11, co-authored 120 publications receiving 454 citations.
Papers
More filters
Proceedings ArticleDOI
Sar Ship Detection Based on Swin Transformer and Feature Enhancement Feature Pyramid Network
TL;DR: Wang et al. as discussed by the authors proposed a SAR ship detection method based on Swin Transformer and Feature Enhancement Feature Pyramid Network (FEFPN) to model long-range dependencies and generate hierarchical features maps.
Journal ArticleDOI
A joint sparse recovery algorithm for coprime adjacent array synthetic aperture radar 3D sparse imaging
TL;DR: In the linear array synthetic aperture radar (LASAR) imaging, the spacing between adjacent elements in the uniform linear array (ULA) must satisfy the Nyquist sampling theore as discussed by the authors.
Proceedings ArticleDOI
Efficient Autofocus for 3-D SAR Sparse Imaging Based on Joint Criterion Optimization
TL;DR: This paper presents an efficient sparse autofocusing algorithm for 3-D SAR imaging based on joint criterion optimization using the least square regularization sparse recovery technique and an autofocus model combined with minimum mean square error criterion and maximum sharpness criterion.
Proceedings ArticleDOI
Maximum Sharpness Based FISTA For SA-BiLASAR 3-D Sparse Autofocus Imaging
TL;DR: An autofocus method is proposed for SA-BiLASAR 3-D sparse imaging based on maximum sharpness estimation (MSE) and results demonstrate the effectiveness of the sparse aut ofocus approach in the case of the different types of motion errors.
Proceedings ArticleDOI
Semi-Supervised Learning-Based Remote Sensing Image Scene Classification Via Adaptive Perturbation Training
TL;DR: In this paper, a semi-supervised learning framework for remote sensing image scene classification is proposed, which is trained by a novel adaptive perturbation training method, which can achieve higher classification accuracy with unlabeled data compared with the corresponding supervised classifier.