OpenMMLab Pre-training Toolbox and Benchmark
Scenic: A Jax Library for Computer Vision Research and Beyond
PyTorch code and models for the DINOv2 self-supervised learning method.
Model Zoo of BDD100K Dataset
Practical New Tasks and Inspiring Modeling Solutions for Diverse Open Vision Problems
Multi-modality pre-training
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
