Add to Favourites
To login click here
Meta has released the first version of I-JEPA, a machine learning (ML) model that learns abstract representations of the world through self-supervised learning on images. Initial tests show that I-JEPA performs strongly on many computer vision tasks and is much more efficient than other state-of-the-art models. Self-supervised learning is inspired by the way humans and animals learn, and AI systems should be able to learn through raw observations without the need for humans to label their training data. Meta has open-sourced the training code and model and will be presenting I-JEPA at the Conference on Computer Vision and Pattern Recognition (CVPR) next week.
