Last year, Meta’s Chief AI Scientist Yann LeCun proposed a new architecture intended to overcome key limitations of even the most advanced AI systems today. His vision is to create machines that can learn internal models of how the world works so that they can learn much more quickly, plan how to accomplish complex tasks, and readily adapt to unfamiliar situations.

We’re excited to introduce the first AI model based on a key component of LeCun’s vision. This model, the Image Joint Embedding Predictive Architecture (I-JEPA), learns by creating an internal model of the outside world, which compares abstract representations of images (rather than comparing the pixels themselves). I-JEPA delivers strong performance on multiple computer vision tasks, and it’s much more computationally efficient than other widely used computer vision models. The representations learned by I-JEPA can also be used for many different applications without needing extensive fine tuning. For example, we train a 632M parameter visual transformer model using 16 A100 GPUs in under 72 hours, and it achieves state-of-the-art performance for low-shot classification on ImageNet, with only 12 labeled examples per class. Other methods typically take two to 10 times more GPU-hours and achieve worse error rates when trained with the same amount of data.
 

Our paper on I-JEPA will be presented at CVPR 2023 next week, and we’re also open-sourcing the training code and model checkpoints today.