CentripetalNet
Introduction
@InProceedings{Dong_2020_CVPR,
author = {Dong, Zhiwei and Li, Guoxuan and Liao, Yue and Wang, Fei and Ren, Pengju and Qian, Chen},
title = {CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
Results and models
Backbone | Batch Size | Step/Total Epochs | Mem (GB) | Inf time (fps) | box AP | Config | Download |
---|---|---|---|---|---|---|---|
HourglassNet-104 | 16 x 6 | 190/210 | 16.7 | 3.7 | 44.8 | config | model | log |
Note:
- TTA setting is single-scale and
flip=True
. - The model we released is the best checkpoint rather than the latest checkpoint (box AP 44.8 vs 44.6 in our experiment).