The Multimodal Learning for Earth and Environment Challenge (MultiEarth 2022) will be the first competition aimed at the monitoring and analysis of deforestation in the Amazon rainforest at any time and in any weather conditions. The goal of the Challenge is to provide a common benchmark for multimodal information processing and to bring together the earth and environmental science communities as well as multimodal representation learning communities to compare the relative merits of the various multimodal learning methods to deforestation estimation under well-defined and strictly comparable conditions. MultiEarth 2022 will have three sub-challenges: 1) matrix completion, 2) deforestation estimation, and 3) image-to-image translation. This paper presents the challenge guidelines, datasets, and evaluation metrics for the three sub-challenges. Our challenge website is available at https://sites.google.com/view/rainforest-challenge.
@article{arxiv.2204.07649,
title = {MultiEarth 2022 -- Multimodal Learning for Earth and Environment Workshop and Challenge},
author = {Miriam Cha and Kuan Wei Huang and Morgan Schmidt and Gregory Angelides and Mark Hamilton and Sam Goldberg and Armando Cabrera and Phillip Isola and Taylor Perron and Bill Freeman and Yen-Chen Lin and Brandon Swenson and Jean Piou},
journal= {arXiv preprint arXiv:2204.07649},
year = {2022}
}