Soft Anchor-Point Object Detection

被引:109
作者
Zhu, Chenchen [1 ]
Chen, Fangyi [1 ]
Shen, Zhiqiang [1 ]
Savvides, Marios [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
来源
COMPUTER VISION - ECCV 2020, PT IX | 2020年 / 12354卷
关键词
Object detection; Anchor-point detector; Soft-weighted anchor points; Soft-selected pyramid levels;
D O I
10.1007/978-3-030-58545-7_6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, anchor-free detection methods have been through great progress. The major two families, anchor-point detection and key-point detection, are at opposite edges of the speed-accuracy trade-off, with anchor-point detectors having the speed advantage. In this work, we boost the performance of the anchor-point detector over the key-point counterparts while maintaining the speed advantage. To achieve this, we formulate the detection problem from the anchor point's perspective and identify ineffective training as the main problem. Our key insight is that anchor points should be optimized jointly as a group both within and across feature pyramid levels. We propose a simple yet effective training strategy with soft-weighted anchor points and soft-selected pyramid levels to address the false attention issue within each pyramid level and the feature selection issue across all the pyramid levels, respectively. To evaluate the effectiveness, we train a single-stage anchor-free detector called Soft Anchor-Point Detector (SAPD). Experiments show that our concise SAPD pushes the envelope of speed/accuracy trade-off to a new level, outperforming recent state-of-the-art anchor-free and anchor-based detectors. Without bells and whistles, our best model can achieve a single-model single-scale AP of 47.4% on COCO.
引用
收藏
页码:91 / 107
页数:17
相关论文
共 37 条
[1]   Cascade R-CNN: Delving into High Quality Object Detection [J].
Cai, Zhaowei ;
Vasconcelos, Nuno .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :6154-6162
[2]  
Chen K, 2019, Arxiv, DOI arXiv:1906.07155
[3]  
Dai JF, 2016, ADV NEUR IN, V29
[4]   Deformable Convolutional Networks [J].
Dai, Jifeng ;
Qi, Haozhi ;
Xiong, Yuwen ;
Li, Yi ;
Zhang, Guodong ;
Hu, Han ;
Wei, Yichen .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :764-773
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]   CenterNet: Keypoint Triplets for Object Detection [J].
Duan, Kaiwen ;
Bai, Song ;
Xie, Lingxi ;
Qi, Honggang ;
Huang, Qingming ;
Tian, Qi .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :6568-6577
[7]  
He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]   Bounding Box Regression with Uncertainty for Accurate Object Detection [J].
He, Yihui ;
Zhu, Chenchen ;
Wang, Jianren ;
Savvides, Marios ;
Zhang, Xiangyu .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :2883-2892
[10]  
Huang LC, 2015, Arxiv, DOI arXiv:1509.04874