首页> 外文会议>Third International Workshop on Pattern Recognition >An Extension of BING to High IOU Threshold
【24h】

An Extension of BING to High IOU Threshold

机译:将BING扩展到较高的IOU阈值

获取原文
获取原文并翻译 | 示例

摘要

BING is an objectness measure to extract proposal windows in an image that may contain objects, avoiding cumbersome sliding window search for object detection. BING has a high recall rate when the Intersection-over-Union (IOU) threshold is 0.5, and runs as fast as 300 fps. However, the recall rate drops rapidly when the IOU threshold is greater than 0.5. So in this paper, we focus on investigating the cause of this phenomenon, and propose how to improve the recall rates, in which average recall rate is used in the performance evaluation of objectness measure for object detection. The problem of less positive samples in the secondary training stage is solved by selecting parameters with respect to training and testing.
机译:BING是一种客观措施,可在可能包含对象的图像中提取建议窗口,从而避免了繁琐的滑动窗口搜索以进行对象检测。当“跨单位交集”(IOU)阈值为0.5时,BING具有较高的召回率,并且运行速度高达300 fps。但是,当IOU阈值大于0.5时,召回率会迅速下降。因此,在本文中,我们将重点研究这种现象的原因,并提出如何提高召回率,其中将平均召回率用于目标检测的客观性指标的性能评估。通过选择与训练和测试相关的参数,可以解决第二训练阶段样本阳性率较低的问题。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号