Help Clean the Oceans with ML on December 5th
Weights & Biases is excited to support the Ocean Cleanup data annotation challenge organized by Kili Technology in partnership with isahit and OVHcloud.
Created on November 5|Last edited on January 12
Comment
We're excited to be part of a new event called the Ocean Cleanup Challenge! What is it? It's a community dataset annotation project with an aim we can all get behind: detecting plastics in the ocean to help fight pollution.
Here are the details:
During the week of the December 5th, ML engineers will join forces to help The Ocean Cleanup in its mission. Organized by Kili Technology and supported by OVHcloud, isahit, and Weights & Biases, this program aims to help the Ocean Cleanup on its mission to boost the efficiency of their plastic detection models and accelerate the cleaning of our oceans.

During the challenge, participants will annotate images from The Ocean Cleanup’s onboard cameras and classifying detected objects. With a mix of human and model annotation to accelerate the labeling process, our collective goal will be to label quickly to create the highest quality dataset.
🏆 Winners of the challenge will be determined on the efficiency & quality of the labeling and will be rewarded with extensive free vouchers for all solutions and swag packs!
What's in it for you?
By participating in this challenge, you’ll be able to:
- Discover a passionate community of data scientists committed to fixing the ecological impacts of our economy.
- Develop your skillset on a suite of new data-science tools.
- Participate in the annotation of 100,000+ images of plastic in oceans and help them to determine where to deploy cleanup to have the most significant impact.
Okay, so how can I participate in the Ocean Cleanup Challenge?
- Dec 5 - Dec 9, 2022
- Participants can join as teams or as single contributors
- Beginners are welcome
Ways to use W&B for the challenge (and how it might help you win)
Weights & Biases is a MLOps platform for tracking and organizing your machine learning experiments and analysis.
To share your learnings with the world, you're encouraged to create a Report including any experimental details that you've tried.
To get started with W&B:
Hint: Look for the wandb.Table code to see how to log your segmentation predictions in an interactive Table
💡
- Experiment with different models or techniques to get the best automated labels
- Share your results within a Report (click "create report" within your W&B project)

Conclusion
If you have a little time in early December to help out and give back, we'd love to again invite you to join the Ocean Cleanup Challenge. And if you'd like a little inspiration, here are a pair of environmental ML reports to get you started:
Add a comment
Iterate on AI agents and models faster. Try Weights & Biases today.