Abstract: Vision GNN (ViG) is a convolutional architecture capable of capturing global image structures by dynamically determining the features to be convolved via graph convolution. Although ViG has ...
Abstract: Graph transformer networks have received more attention in hyperspectral image (HSI) classification. However, they overlooked the influence of graph connectivity strength in positional ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback