VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Object detection. EfficientDet-D5 level COCO AP in 20 epochs. SOTA single-stage detector on Waymo Open Dataset.
Official code for BEVDepth.
A Collection of Variational Autoencoders (VAE) in PyTorch.
What Makes for End-to-End Object Detection, ICML2021
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
PoolFormer: MetaFormer is Actually What You Need for Vision