Skip to content
Publications

Article · Computers, materials & continua/Computers, materials & continua · January 1, 2024

Improving Generalization for Hyperspectral Image Classification: The Impact of Disjoint Sampling on Deep Models

Muhammad Imran Ahmad, Manuel Mazzara, Salvatore Distefano, Adil Khan, Hamad Ahmed Altuwaijri

Abstract

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models e.g., Attention Graph and Vision Transformer. When training, validation, and test sets overlap or share data, it introduces ... | Find, read and cite all the research you need on Tech Science Press

Remote-Sensing Image ClassificationAdvanced Neural Network ApplicationsSpectroscopy and Chemometric Analyseshyperspectral image classificationgeneralizationvision transformer

More by Manuel Mazzara