## Task detail 

Participants are tasked with crafting an algorithm that boasts outstanding generalization capabilities, utilizing training data confined to a particular region in Japan. This algorithm must possess the precision and autonomy to identify and delineate building footprints from satellite imagery, which geographically diverges from the training dataset. The core of this extraction endeavor hinges on pinpointing the exact coordinates of each building's boundary vertices with high accuracy. 

We place no limitations on the algorithmic approaches’ participants may choose to adopt. We strongly advocate for the exploration of a broad spectrum of innovative algorithms, cutting-edge review-stage techniques, or established methods across supervised, weakly supervised, or unsupervised learning paradigms. Additionally, participants are encouraged to venture into the amalgamation of open-source data with established public datasets, such as OpenStreetMap (OSM), within their research and development activities. It's important to note, however, that the creation and utilization of any manually generated supplementary datasets are strictly forbidden.

## Further reading
- Chen, S., Ogawa, Y., Zhao, C., & Sekimoto, Y. (2023). Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach. ISPRS Journal of Photogrammetry and Remote Sensing, 195, 129-152.