Meta's Multilingual AI Models: Open-Source and Bible-Powered.
TL;DR
Meta AI Research has open-sourced DINOv2, a pretrained foundation model for computer vision tasks, including image classification, video action recognition, semantic segmentation, and depth estimation. DINOv2 is based on the Vision Transformer architecture and is trained on a curated dataset of 142M images. It outperforms other self-supervised learning models and shows performance comparable to or better than that of weakly-supervised models. The model is available on GitHub, and an interactive demo of several computer vision tasks using DINOv2 is available on the project site.
Topics:technologyartificial-intelligence#artificial-intelligence#computer-vision#dinov2#meta-ai-research#pretrained-model#ssl
- Meta Open-Sources Computer Vision Foundation Model DINOv2 InfoQ.com
- Meta's open-source speech AI models support over 1,100 languages AI News
- The Dire Defect of 'Multilingual' AI Content Moderation WIRED
- Meet BLOOMChat: An Open-Source 176-Billion-Parameter Multilingual Chat Large Language Model (LLM) Built on Top of the BLOOM Model MarkTechPost
- Meta used the Bible to train AI models to learn over 1,000 languages Interesting Engineering
Want the full story? Read the original reporting
Read on InfoQ.com