anchor-free

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

🔥🔥🔥YOLOv5, YOLOv6, YOLOv7, YOLOv8, PPYOLOE, YOLOX, YOLOR, YOLOv4, YOLOv3, Transformer, Attention, TOOD and Improved-YOLOv5-YOLOv7... Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

face detection

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

This is the implementation of GGHL (A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection)

[ECCV'20] Ocean: Object-aware Anchor-Free Tracking

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

The official PyTorch Implementation of RTM3D and KM3D for Monocular 3D Object Detection

FoveaBox: Beyond Anchor-based Object Detector

Keras beit,botnet,CMT,CoaT,CoAtNet,convnext,cotnet,davit,efficientdet,edgenext,efficientformer,efficientnet,fbnet,flexivit,gcvit,ghostnet,gmlp,gpvit,halonet,hornet,iformer,lcnet,levit,maxvit,mlp-mixer,mobilevit,nat,nfnets,pvt,regnet,resmlp,resnest,resnext,resnetd,swin,tinynet,uniformer,volo,wavemlp,yolor,yolov7,yolox

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID

Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

list the paper for recently anchor free detector

unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection

an edge-real-time anchor-free object detector with decent performance

NAS-FCOS: Fast Neural Architecture Search for Object Detection (CVPR 2020)

Instance Segmentation based on CenterNet and CondInst

A pure torch implement of FCOS 37.2AP