(1) rskg.xlsx is the source file of remote sensing knowledge graph (RSKG)
run import_kg.py can import rskg. xlsx into the local neo4j database
rskg.svg stands for the visual result of RSKG in neo4j
(2) sr-rskg.npy denotes the semantic vectors of 70 scene categories via TransH based on RSKG
(3) visual images of 70 scene categories have also been publicly released.
https://pan.baidu.com/s/1KnECNqgw6TRVojBQZ1ZuLA
password: 9999
If you find the aforementioned data helpful in your work, please kindly cite the following papers:
[1] Y. Li, D. Kong, Y. Zhang, Y. Tan, and L. Chen. Robust deep alignment network with remote sensing knowledge graph for zero-shot and generalized zero-shot remote sensing image scene classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2021.
[2] Y. Li, Z. Zhu, J. Yu, and Y. Zhang. Learning deep cross-modal embedding networks for zero-shot remote sensing image scene classification. IEEE Transactions on Geoscience and Remote Sensing. 2021.
[3] Y. Li, Y. Zhang, and Z. Zhu. Error-tolerant deep Learning for remote sensing image scene classification. IEEE Transactions on Cybernetics. 2021, 51(4): 1756-1768.