⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8MB and run 97FPS on cellphone🔥

pip install antialiased-cnns to improve stability and accuracy

RepVGG: Making VGG-style ConvNets Great Again

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

face profile augmentation in 3ddfa. profile face synthesis from frontal face

[CVPR 20] G3AN: Disentangling Appearance and Motion for Video Generation

papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face D…

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

📖 A curated list of resources dedicated to talking face.

GIF is a photorealistic generative face model with explicit 3D geometric and photometric control.

Convert from Basel Face Model (BFM) to the FLAME head model

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

A Modular, Configuration-Driven Framework for Knowledge Distillation

A curated list of awesome self-supervised methods

[ECCV 2020] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis

A curated list of long-tailed recognition resources.

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

Deep Snake for Real-Time Instance Segmentation,pytorch1.0,cuda8.0

A resource repository for 3D machine learning

FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (CVPR2020)

[NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2…

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

Code for visualizing the loss landscape of neural nets

Repository of notes, code and notebooks for the book Pattern Recognition and Machine Learning by Christopher Bishop

An unofficial toy implementation for NVAE 《A Deep Hierarchical Variational Autoencoder》