Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection | |
Zhang, Shifeng1,4; Chi, Cheng1,5; Yao, Yongqiang2; Lei, Zhen1,4; Li, Stan Z.3 | |
2020 | |
会议日期 | 2020-06-08 |
会议地点 | h美国华盛顿 |
英文摘要 | Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to 50.7% AP without introducing any overhead. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39039] |
专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
通讯作者 | Lei, Zhen |
作者单位 | 1.University of Chinese Academy of Sciences 2.Beijing University of Posts and Telecommunications 3.Westlake University 4.Institute of Automation Chinese Academy of Sciences 5.Aerospace Information Research Institute Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhang, Shifeng,Chi, Cheng,Yao, Yongqiang,et al. Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection[C]. 见:. h美国华盛顿. 2020-06-08. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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