Access record for datasets in MSFNet: LoveDA and Vaihingen

This Zenodo record provides direct access links, official DOIs, and standardized citations for the two public datasets used in "MSFNet: A Multi-Source Fusion Network for Semantic Segmentation of High-Resolution Remote Sensing Images." The actual data files remain at their original public repositories. • LoveDA dataset: https://doi.org/10.5281/zenodo.5706578• Vaihingen dataset: https://www.isprs.org/resources/datasets/benchmarks/UrbanSemLab/2d-sem-label-vaihingen.aspx Standardized citations (for reference list):Wang, J., Zheng, Z., Ma, A., Lu, X., & Zhong, Y. (2021). LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.5706578ISPRS. (2014). 2D Semantic Labeling Contest – Vaihingen data. ISPRS Benchmark. Available at: https://www.isprs.org/resources/datasets/benchmarks/UrbanSemLab/2d-sem-label-vaihingen.aspx (accessed: 21 March 2026). This record is created to ensure full compliance with the journal GIScience & Remote Sensing's Open + FAIR data policy. Licensed under CC-BY 4.0.