2026-10-11T10:26:28Z https://www.scidb.cn/oai

10.57760/sciencedb.40215 2026-08-04T09:33:15Z

2026-08-04 Optical-SAR Fine-Grained Zero-Shot Learning doi:10.57760/sciencedb.40215 en The name of this dataset is Optical-SAR Fine-Grained Zero-Shot Learning" (OS-FGZSL)， This dataset is designed for optical assisted SAR target zero sample fine-grained classification tasks, mainly used to support cross modal category association, feature alignment, unknown category recognition, and related algorithm evaluation between SAR images and optical remote sensing images. The data sources of this dataset include SAR images and optical remote sensing images. Among them, SAR images mainly come from open-source SAR target datasets such as SAR-AIRcraft-1.0, SAR-ACD, FAIR-CSAR, FUSAR Ship, and OpenSARShip; The optical images are mainly sourced from the FAIR1M/FAIR1M2.0 high-resolution optical remote sensing target dataset. The source data covers typical remote sensing target types such as aircraft, ships, and bridges, including airports, ports, rivers, nearshore areas, cities, and towns. The time range of the integrated data is from 2017 to 2024, with a geographic coverage mainly covering regions such as Asia, Europe, and North America, and a spatial resolution of better than 20m. The data generation process mainly includes target instance pruning, quality screening, category semantic normalization, and data organization. Firstly, based on the annotation file of the original dataset, crop a single target image from the remote sensing image; Subsequently, samples with poor quality or incomplete targets are removed, and semantically consistent but named categories from different data sources are unified under standard category names, ultimately forming a category level aligned SAR optical cross modal dataset. The dataset contains a total of 147302 target images, including 66384 SAR images and 80918 optical images, covering 17 fine-grained target categories. The data formats include. png,. jpg, *. tif, and *. tif. The data directory adopts a three-level structure of "category modality image" organization, that is, SAR and Optical subdirectories are set separately under each target category to store the target image samples of the corresponding modality.  SAR; Optical remote sensing; Fine-grained image; OS-FGZSL; optical Li Xun Zhao Lijun Ren Ruotian Yang Rui Cui Shaolong PUBLIC https://opendatacommons.org/licenses/by/1-0/ dataset Science Data Bank