meta Meta Unveils DINO for Unsupervised Computer Vision Object Segmentation Meta introduces DINO, a self-supervised Vision Transformer method that achieves state-of-the-art computer vision results while automatically segmenting objects without any labeled data or specific segmentation objectives.
vision transformers Self-Supervised Vision Transformers Reveal Surprising New Capabilities Researchers introduce DINO, a self-supervised method that gives Vision Transformers unique properties like explicit semantic segmentation without labels. The approach achieves 80.1% top-1 accuracy on ImageNet using linear evaluation.
facebook Facebook Trains Billion-Parameter Image AI Using One Billion Unlabeled Instagram Photos Facebook develops SEER, a massive computer vision model that partly teaches itself by grouping one billion public Instagram images before fine-tuning on labeled data.
facebook Facebook Builds Massive AI by Training on One Billion Instagram Photos Facebook develops SEER, a billion-parameter computer vision system that learns to recognize objects by pretraining itself on a billion unlabeled Instagram images before fine-tuning on labeled data.
artificial intelligence AI Tackles Piano Playing and Unfolds Sealed 17th Century Letters Researchers use computer vision to recreate piano music from silent video and deploy advanced algorithms to virtually unfold fragile historical letters. These creative applications show how artificial intelligence extends into arts and humanities.
facebook Facebook Unveils SEER: AI Model That Learns to Recognize Images Without Labels Facebook introduces SEER, a self-supervised AI model that teaches itself to identify objects in photos using unlabeled Instagram data. The breakthrough system outperforms existing models while significantly reducing training time.
facebook Facebook Unveils SEER, a Self-Teaching AI Model for Image Recognition Facebook introduces SEER, a self-supervised AI that learns to recognize images without human-labeled data. The model achieves state-of-the-art accuracy by training on a billion random Instagram photos.
facebook Facebook Unveils Vision AI That Learns Like a Human Infant Facebook introduces a new artificial intelligence system called SEER that learns from unlabeled images, drastically reducing the need for expensive data labeling. This breakthrough allows AI to understand the world through observation, much like a baby learns.
facebook Facebook Builds AI That Learns to See Using One Billion Instagram Photos Facebook develops a new artificial intelligence program named SEER that learns to identify objects by analyzing one billion random, unlabeled Instagram images. The self-supervised learning model outperforms existing AI systems and promises future improvements in accessibility and content moderation.
clip New Visual AI Model Learns From Text Instead of Fixed Labels Researchers introduce a visual model that learns by matching internet images with text captions, bypassing the need for predetermined object categories. The system achieves impressive zero-shot performance across dozens of computer vision tasks.
aws AWS Launches Lookout for Vision to Automate Manufacturing Defect Detection Amazon Web Services introduces Lookout for Vision, a fully managed machine learning service that automates visual inspection to spot product defects in industrial environments. The tool replaces complex, hard-coded rules with deep learning models that adapt to varying lighting and camera angles.
aws AWS Launches Lookout for Vision to Automate Manufacturing Defect Detection Amazon introduces Lookout for Vision, a fully managed machine learning service that automates visual inspection to spot product defects in industrial environments. The tool replaces complex, rule-based systems with deep learning models that adapt to real-world manufacturing conditions.
amazon Amazon Launches AI Vision Service to Catch Manufacturing Defects Amazon introduces Lookout for Vision, a cloud service that uses computer vision to automatically spot product anomalies on manufacturing lines. The tool requires as few as 30 images to train an AI model and operates on a pay-as-you-go basis.
text-to-image Simple Transformer Achieves Zero-Shot Text-to-Image Generation Without Complex Training Researchers introduce a straightforward transformer approach that models text and image tokens together as a single data stream. This scaled-up method successfully competes with domain-specific models without relying on auxiliary losses or segmentation masks.
text-to-image New Transformer Approach Achieves Zero-Shot Text-to-Image Generation Researchers introduce a simple transformer model that autoregressively processes text and image tokens together as a single data stream. This scaled approach matches previous domain-specific models in zero-shot evaluations without needing complex architectures or auxiliary training data.