4 papers
Geometry-Calibrated Closed-Form Shrinkage for SAR Despeckling
Xuran Hu, Mingzhe Zhu, Djordje Stanković +4
Synthetic aperture radar (SAR) despeckling is an inverse-recovery problem in which multiplicative non-Gaussian noise must be suppressed without erasing scattering structures. We re…
GraphNNK -- Graph Classification and Interpretability
Zeljko Bolevic, Milos Brajovic, Isidora Stankovic +1
Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax l…
Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
Xuran Hu, Mingzhe Zhu, Zhenpeng Feng +2
The inherent "black box" nature of deep neural networks (DNNs) compromises their transparency and reliability. Recently, explainable AI (XAI) has garnered increasing attention from…
Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation
Xuran Hu, Mingzhe Zhu, Ziqiang Xu +2
Generative Adversarial Networks (GANs) have shown tremendous potential in synthesizing a large number of realistic SAR images by learning patterns in the data distribution. Some GA…