Unifying Classification and Bounding Box Regression Head for Object Detection
文献类型：会议论文
| 作者 | Gao CZ(高存璋)2,3,4; Gu HT(谷海涛)3,4 ; Yu SQ(余思泉)3,4; Li, Xingzhen1
|
| 出版日期 | 2021 |
| 会议日期 | December 3-5, 2021 |
| 会议地点 | Virtual, Online |
| 页码 | 1-8 |
| 英文摘要 | Object detection usually includes two parts: objection classification and location. At present, the popular object detectors usually use two detection heads: one head is used to predict classification score, and the other one is used to predict the bounding box (bbox), respectively. In this paper, we first stack classification head after feature extract convolutional neural networks of bbox regression head. Then, we establish the classification networks by using a bounding box feature. The bounding box feature is very useful when the classification head uses soft Intersection over Union (IoU) labels. In experiment parts, only using PASCAL VOC 2007 datasets, soft Centerness labels, and soft IoU labels get 50.06 mAP and 52.08 mAP on VOC 2007 test. Compared with FCOS, they have 1.08% and 1.12% improvements. Using PASCAL VOC 2007 and 2012 datasets, our Union A*B head gets 78.71mAP after 12 epochs training with ResNet-101 as backbone and FPN as the neck. Extensive experimental results show that the proposed algorithm is superior to other detection methods. |
| 产权排序 | 1 |
| 会议录 | 2021 3rd International Conference on Robotics, Intelligent Control and Artificial Intelligence, ICRICA 2021
 |
| 会议录出版者 | IOP Publishing Ltd |
| 会议录出版地 | Bristol, UK |
| 语种 | 英语 |
| ISSN号 | 1742-6588 |
| 源URL | [http://ir.sia.cn/handle/173321/30823]  |
| 专题 | 沈阳自动化研究所_海洋信息技术装备中心 |
| 通讯作者 | Gao CZ(高存璋) |
| 作者单位 | 1.Shenyang University of Technology Shenyang, Liaoning, China 2.University of Chinese Academy of Sciences Shenyang, Liaoning, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Liaoning, China 4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China |
| 推荐引用方式 GB/T 7714 | Gao CZ,Gu HT,Yu SQ,et al. Unifying Classification and Bounding Box Regression Head for Object Detection[C]. 见:. Virtual, Online. December 3-5, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。