Summary of Fields Of the World: a Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation, by Hannah Kerner et al.
Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation
by Hannah Kerner, Snehal Chaudhari, Aninda Ghosh, Caleb Robinson, Adeel Ahmad, Eddie Choi, Nathan Jacobs, Chris Holmes, Matthias Mohr, Rahul Dodhia, Juan M. Lavista Ferres, Jennifer Marcus
First submitted to arxiv on: 24 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel machine learning (ML) benchmark dataset for agricultural field instance segmentation, called Fields of The World (FTW). The goal is to develop ML methods that can automatically extract crop field boundaries from remotely sensed images, which could help realize the demand for these datasets at a global scale. Current ML methods lack sufficient geographic coverage, accuracy, and generalization capabilities, while research on improving them is restricted by the lack of labeled datasets representing the diversity of global agricultural fields. The FTW dataset spans 24 countries across four continents and consists of 70,462 samples, each containing instance and semantic segmentation masks paired with multi-date, multi-spectral Sentinel-2 satellite images. Baseline models for the new FTW benchmark are provided, showing that models trained on FTW have better zero-shot and fine-tuning performance in held-out countries than models that aren’t pre-trained with diverse datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a big dataset to help machines learn to find boundaries between different types of crops from satellite images. Right now, it’s hard to make computers do this job because we don’t have enough training data that shows what the answers should be. The new dataset has lots of pictures and labels (like maps) for over 70,000 areas where different crops grow. This could help computers get better at recognizing crop boundaries and might even work in countries it was trained on. |
Keywords
» Artificial intelligence » Fine tuning » Generalization » Instance segmentation » Machine learning » Semantic segmentation » Zero shot
