Citing the project

If you use the models, dataset or pipeline in your own project - either for research or commercially - we politely ask that you provide a citation. This encourages repeatable research and helps us to better understand who is using the project and how we can improve it in the future.

As a "catch all" you can cite our arXiv paper (this reference will be updated once the work has been peer-reviewed):

@misc{veitchmichaelis2024oamtcdgloballydiversedataset,
      title={OAM-TCD: A globally diverse dataset of high-resolution tree cover maps}, 
      author={Josh Veitch-Michaelis and Andrew Cottam and Daniella Schweizer and Eben N. Broadbent and David Dao and Ce Zhang and Angelica Almeyda Zambrano and Simeon Max},
      year={2024},
      eprint={2407.11743},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.11743}, 
}

Model citation

All the models hosted on HuggingFace have individal Document Object Identifiers (DOIs) so if you feel it is more appropriate to cite a model specifically, you can find DOI information on either our model zoo page or the specific model repositories. These DOIs are generated by HuggingFace.

Dataset citation

Please cite the paper if you use the dataset in a new project. The dataset is also versioned, as we are likely to modify and improve it in the future. You can find our initial release DOIs on HuggingFace or Zenodo.

Pipeline citation

Similarly to the dataset, we will provide a DOI for the release configuration of the pipeline, but as it's under active development things are likely to change. We suggest that if you are referencing or using the pipeline in a different project, you use a tagged release and consider pinning to a specific commit if using as a dependency.