EurekAlert!

PolyU develops novel AI graph neural network models to unravel interdisciplinary complexities in image recognition and neuroscience

As an emerging technology in the field of artificial intelligence (AI), graph neural networks (GNNs) are deep learning models ...
IEEE

FreqSpaceNet: Integrating Frequency and Spatial Domains for Remote Sensing Image Segmentation

Abstract: Semantic segmentation of remote sensing images aims to assign semantic labels to each pixel in the image, serving as a key technology for achieving precise ground object interpretation.
IEEE

Dual-Graph Knowledge Distillation Meets Multiscale CNN: A Novel Ensemble Approach for Few-Shot Hyperspectral Image Classification

Hyperspectral image (HSI) classification aims at categorizing each pixel in an HSI, facilitating precise identification and differentiation of various land cover types. In recent years, graph neural ...