nerminsamet

CenterNet2

Two-stage CenterNet

deq

[NeurIPS'19] Deep Equilibrium Models

SAN

Exploring Self-attention for Image Recognition, CVPR2020.

deep-face-alignment

The MXNet Implementation of Stacked Hourglass and Stacked SAT for Robust 2D and 3D Face Alignment

eenets.pytorch

Pytorch implementation of EENets

AdvSegLoss

Official Pytorch implementation of Adversarial Segmentation Loss for Sketch Colorization [ICIP 2021]

conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

ObjectNetReanalysis

reanalysis of the ObjectNet paper and our annotations and code

xcenternet

Fast anchor free Object Detection based on CenterNet (Objects As Points) and TTFNet (Training-Time-Friendly Network). Implemented in TensorFlow 2.4+.

google-landmark

Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

COCO-WholeBody

ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

SparseR-CNN

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

mega.pytorch

Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020

Pytorch_Retinaface

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

wetectron

Weakly-supervised object detection.

machine-learning-cheat-sheet

Classical equations and diagrams in machine learning

Objectron

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

vision_transformer

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

aLRPLoss

Official PyTorch Implementation of aLRP Loss [NeurIPS2020]

fiftyone

The open-source tool for building high-quality datasets and computer vision models

SeqNet

Joint Learning of Vessel Segmentation and Artery/Vein Classification

nerf-pytorch

A PyTorch re-implementation of Neural Radiance Fields

temporal-consistency

BMVC 2020 self-supervised learning code

Text-Attribute-Aggregation-and-Visual-Feature-Decomposition-for-Person-Search

CornerNet-Lite

CNNs-With-Label-Noise

code for the paper "The Resistance to Label Noise in K-NN and DNN Depends on its Concentration" by Amnon Drory, Oria Ratzon, Shai Avidan and Raja Giryes

AdaLAM

AdaLAM is a fully handcrafted realtime outlier filter integrating several best practices into a single efficient and effective framework. It detects inliers by searching for significant local affine patterns in image correspondences.

FPT

Implementation for paper: Feature Pyramid Transformer

FunnelAct