2026-10-14T15:03:41Z https://www.scidb.cn/oai

10.57760/sciencedb.space.03632 2026-06-05T11:04:32Z

2026-06-05 NWPU-RESISC45 Dataset doi:10.57760/sciencedb.space.03632 en The NWPU-RESISC45 Dataset is a remote sensing image dataset created by Northwestern Polytechnical University. It contains 31,500 images (256*256 pixels) covering 45 categories, with 700 images per category. Images with the suffixes 28, 69, 55, 60, 74, and 97.png were extracted as the test set, totaling 6*7*45=1890 images. The remaining 29,610 images were used as the training set. The Bicubic degradation algorithm was then applied to further process the images into x4 HR and LR image pairs. Remote sensing images; Scene classification; Image super-resolution; NWPU-RESISC45; High-resolution remote sensing images; Deep learning Liu Hui Zhou Hai PUBLIC https://creativecommons.org/publicdomain/zero/1.0/ dataset Science Data Bank