Abstract: In hyperspectral image (HSI) classification, Transformer and CNN are widely used because they complement each other in extracting features. Nevertheless, existing Transformer-based methods ...
Abstract: Imbalanced image classification faces critical challenges in balancing the quality and diversity of synthetic minority samples. This article proposes the improved estimation distribution ...
As shown below, the inferred masks predicted by our segmentation model trained on the dataset appear similar to the ground truth masks, but they lack precision in certain areas. Concrete structures ...