There are 1 repository under anchor-free topic.
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation
[ECCV'20] Ocean: Object-aware Anchor-Free Tracking
The official PyTorch Implementation of RTM3D and KM3D for Monocular 3D Object Detection
Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID
unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection
list the paper for recently anchor free detector
Instance Segmentation based on CenterNet and CondInst
Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"
使用OpenCV部署YOLOX,支持YOLOX-S、YOLOX-M、YOLOX-L、YOLOX-X、YOLOX-Darknet53五种结构,包含C++和Python两种版本的程序
YOLOv8 implementation using PyTorch
使用OpenCV部署SCRFD人脸检测,包含C++和Python两种版本的程序实现,本套程序只依赖opencv库就可以运行, 从而彻底摆脱对任何深度学习框架的依赖。
分别使用OpenCV、ONNXRuntime部署NanoDet-Plus,包含C++和Python两个版本的程序
用opencv部署nanodet目标检测,包含C++和Python两种版本程序的实现
fcos implementation in pytorch1.x
FCOS: Fully Convolutional One-Stage Object Detection.
Code for our paper "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection".
使用ONNXRuntime部署anchor-free系列的YOLOR,包含C++和Python两种版本的程序
使用OpenCV部署FastestDet,包含C++和Python两种版本的程序。模型文件不超过1M
:rotating_light::rotating_light::rotating_light: CornerNet:基于虚拟仿真环境下的自动驾驶交通标志识别
使用ONNXRuntime部署PicoDet目标检测,包含C++和Python两个版本的程序
FCOS: Fully Convolutional One-Stage Object Detection.
A collection of some awesome public Anchor-Free object detection series projects.
YOLO Series