Knowledge Commons of Institute of Automation,CAS
DLA: Dynamic Label Assignment for Accurate One-stage Object Detection | |
He, Jiang1,2; Junrui, Xiao1,2; Qingyi, Gu1 | |
2022-06-06 | |
会议名称 | 2022 11th International Conference on Software and Computer Applications |
会议日期 | 2022-2 |
会议地点 | Malaysia |
摘要 | One-stage object detector has been the most widely used framework in modern object detection due to its excellent performance and high efficiency. Label assignment, which is designed to discriminate positive and negative samples in training process, is closely correlated to the detection performance of one-stage detectors. Previous works commonly utilize geometric prior such as anchor box or key point to determine positive samples. Despite its simplicity, the heuristic strategy is rigid and it might limit the upper bound of detection performance. By introducing extra semantic information, prediction-aware geometric score and sample re-weighting mechanism, we propose a novel strategy called Dynamic Label Assignment in this paper. To validate the effectiveness and generalization of our method, we conduct extensive experiments on the MS COCO dataset. Without bells and whistles, our best model with ResNeXt-101 as backbone achieves state-of-the-art 46.5 AP, surpassing other strong methods such as SAPD (45.4 AP), ATSS (45.6 AP), and GFL (46.0 AP) by a large marigin. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48642 |
专题 | 中科院工业视觉智能装备工程实验室_精密感知与控制 中国科学院自动化研究所 |
通讯作者 | Qingyi, Gu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | He, Jiang,Junrui, Xiao,Qingyi, Gu. DLA: Dynamic Label Assignment for Accurate One-stage Object Detection[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
DLA.pdf(722KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论