Google's Image-Text AI LIMoE Outperforms CLIP on ImageNet Benchmark

Researchers at Google Brain recently trained Language-Image Mixture of Experts (LIMoE), a 5.6B parameter image-text AI model. In zero-shot learning experiments on ImageNet, LIMoE outperforms CLIP and performs comparably to state-of-the-art models while using fewer compute resources.

ai benchmark clip computer vision deep learning google image imagenet ml & data engineering neural networks news text