Skip to content

Latest commit

 

History

History

centernet

English | 简体中文

CenterNet (CenterNet: Objects as Points)

Table of Contents

Introduction

CenterNet is an Anchor Free detector, which model an object as a single point -- the center point of its bounding box. The detector uses keypoint estimation to find center points and regresses to all other object properties. The center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors.

Model Zoo

CenterNet Results on COCO-val 2017

backbone input shape mAP FPS download config
DLA-34(paper) 512x512 37.4 - - -
DLA-34 512x512 37.6 - model config
ResNet50 + DLAUp 512x512 38.9 - model config
MobileNetV1 + DLAUp 512x512 28.2 - model config
MobileNetV3_small + DLAUp 512x512 17 - model config
MobileNetV3_large + DLAUp 512x512 27.1 - model config
ShuffleNetV2 + DLAUp 512x512 23.8 - model config

Citations

@article{zhou2019objects,
  title={Objects as points},
  author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},
  journal={arXiv preprint arXiv:1904.07850},
  year={2019}
}