Challenge

OmniLabel benchmark: Novel dataset with complex, free-form text descriptions of objects. Checkout https://www.omnilabel.org and https://arxiv.org/abs/2304.11463 for details

Train on public datasets and evaluate on our benchmark! We define three tracks to compete - A, B, and C. They differ in the allowed training data.

Test set and validation sets are available (v0.1.3). Use our evaluation server to test your model on both sets and participate in the challenge. Use our our toolkit to evaluate a model on the validation set by yourself.

$10,000 prize money will be distributed among the participants of the challenge!

Timeline