5 papers
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…
Manifold-based Shapley for SAR Recognization Network Explanation
Xuran Hu, Mingzhe Zhu, Yuanjing Liu +2
Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost s…
Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image Classification
Zhenpeng Feng, Hongbing Ji, Milos Dakovic +3
Despite the tremendous success of convolutional neural networks (CNNs) in computer vision, the mechanism of CNNs still lacks clear interpretation. Currently, class activation mappi…
Analytical Interpretation of Latent Codes in InfoGAN with SAR Images
Zhenpeng Feng, Milos Dakovic, Hongbing Ji +2
Generative Adversarial Networks (GANs) can synthesize abundant photo-realistic synthetic aperture radar (SAR) images. Some recent GANs (e.g., InfoGAN), are even able to edit specif…