Z
Zongyong Cui
Researcher at University of Electronic Science and Technology of China
Publications - 46
Citations - 755
Zongyong Cui 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 7, co-authored 32 publications receiving 255 citations.
Papers
More filters
Journal ArticleDOI
Dense Attention Pyramid Networks for Multi-Scale Ship Detection in SAR Images
TL;DR: Experiments show that the proposed DAPN method can detect multi-scale ships in different scenes of SAR images with extremely high accuracy and outperforms other ship detection methods implemented on SSDD.
Journal ArticleDOI
Image Data Augmentation for SAR Sensor via Generative Adversarial Nets
TL;DR: Compared with the traditional data linear generation method, the proposed SAR image data augmentation method shows significant improvement on the quantity and quality of the training samples, and can effectively solve the problem of the small sample recognition.
Journal ArticleDOI
Open Set Incremental Learning for Automatic Target Recognition
TL;DR: Experimental results demonstrate that the proposed OSmIL outperforms the other state of the arts on the accuracy of multiclass OSR and can maintain good accuracy and efficiency in the incremental learning experiment set.
Journal ArticleDOI
A Gradually Distilled CNN for SAR Target Recognition
TL;DR: A micro CNN (MCNN) for real-time SAR recognition system is proposed, which has only two layers, and it is compressed from a deep convolutional neural network (DCNN) with 18 layers by a novel knowledge distillation algorithm called gradual distillation, which makes MCNN a better learning route than traditional knowledgedistillation.
Journal ArticleDOI
LDGAN: A Synthetic Aperture Radar Image Generation Method for Automatic Target Recognition
TL;DR: An entirely new loss function is defined for the LDGAN, which utilizes the Wasserstein distance to replace the original distance measurement of the conventional generative adversarial networks (GANs), thus efficiently avoiding the collapse mode problem.