Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

[IJCAI 2020] A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time

Fast Block Sparse Matrices for Pytorch

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

Approximate nearest neighbor search with product quantization on GPU in pytorch and cuda

[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy https://visdom.dev

Code for "Learning to Segment Rigid Motions from Two Frames". CVPR 2021.

Codebase for ICRA 2020 paper "Towards Practical Multi-object Manipulation using Relational Reinforcement Learning"

PyTorch implementation of “Negative Margin Matters: Understanding Margin in Few-shot Classification”

[ECCV'20 Spotlight] Memory-augmented Dense Predictive Coding for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

💦 Seamless, distributed, real-time integration of Blender into PyTorch data pipelines

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Unsupervised Learning by Predicting Noise

a Realistic and Rich 3D Environment

An alarm clock that plays your favorite NPR podcast

Support powerful visual logging in PyTorch.

PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400