The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".

Eye Tracking for Everyone

Confidence-Aware Learning for Deep Neural Networks (ICML2020)

Testing the chirality of digital imaging operations.

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up…

95.16% on CIFAR10 with PyTorch

Code for paper `Disentangled Inference for GANs with Latently Invertible Autoencoder`

Code for paper `Interpreting the Latent Space of GANs for Semantic Face Editing`

1st place models in Google OpenImage Detection Challenge 2019

A collection of AWESOME things about domian adaptation

A curated list of resources for Learning with Noisy Labels

A simple face detect and alignment method, which is easy and stable.

This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

Disentangled Speech Embeddings using Cross-Modal Self-Supervision

Open MMLab Detection Toolbox and Benchmark

This is an unofficial implementation for the 2019 ICCV paper 'Decorrelated Adversarial Learning for Age-Invariant Face Recognition' from Tencent AI Lab

CVPR 2020 论文开源项目合集

Pixel-Adaptive Convolutional Neural Networks (CVPR '19)

Image augmentation for machine learning experiments.

Selective Refinement Network for High Performance Face Detection, AAAI, 2019

Google AI Research

Represent Visual Objects by Point Sets

Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST

yolov3 with mobilenet v2 and ASFF

Pytorch implementation of Stronger-Yolo with channel pruning and Mobiledevice deployment.

Retinaface get 80.99% in widerface hard val using mobilenet0.25.