Frugal AI Challenge

The goal of the Frugal AI Challenge is to encourage both academic and industry actors to keep efficiency in mind when deploying AI models.

By tracking both energy consumption and performance for different AI for climate tasks, we can incentivize frugality in AI deployment while also addressing real-world challenges.

We have chosen three tasks across three modalities, all of which are useful in the global fight against the climate crisis: detecting climate disinformation, classifying regions at risk of wildfires, and detecting illegal deforestation. We will evaluate both performance and efficiency on each of the datasets, based on the real-world constraints of each task and the energy used.

We will announce more details about the tasks and release the datasets soon!