A large-scale image-text dataset benchmark for farmland segmentation

We introduced language-based descriptions of farmland and developed FarmSeg-VL dataset—the first fine-grained image-text dataset designed for spatiotemporal farmland segmentation. The FarmSeg-VL exhibits significant spatiotemporal characteristics. In terms of the temporal dimension, it covers all four seasons. In terms of the spatial dimension, it covers eight typical agricultural regions across China, with a total area of approximately 4,300 km². In addition, in terms of captions, FarmSeg-VL covers rich spatiotemporal characteristics of farmland, including its inherent properties, phenological characteristics, spatial distribution, topographic and geomorphic features, and the distribution of surrounding environments.

If you find this project useful in your research, please consider citing:

[1] Tao, C., Zhong, D., Mu, W., Du, Z., and Wu, H.: A large-scale image-text dataset benchmark for farmland segmentation, Earth Syst. Sci. Data Discuss. [preprint], https://doi.org/10.5194/essd-2025-184, in review, 2025.

[2] H. Wu, Z. Du, D. Zhong, Y. Wang and C. Tao, "FSVLM: A Vision-Language Model for Remote Sensing Farmland Segmentation," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-13, 2025, Art no. 4402813, doi: 10.1109/TGRS.2025.3532960.

[3] Haiyang Wu, Weiliang Mu, Dandan Zhong, Zhuofei Du, Haifeng Li, Chao Tao, FarmSeg_VLM: A farmland remote sensing image segmentation method considering vision-language alignment, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 225, 2025,Pages 423-439.