...
首页> 外文期刊>Circuits and Systems for Video Technology, IEEE Transactions on >Local Metric Learning for Exemplar-Based Object Detection
【24h】

Local Metric Learning for Exemplar-Based Object Detection

机译:基于样本的目标检测的局部度量学习

获取原文
获取原文并翻译 | 示例
           

摘要

Object detection has been widely studied in the computer vision community and it has many real applications, despite its variations, such as scale, pose, lighting, and background. Most classical object detection methods heavily rely on category-based training to handle intra-class variations. In contrast to classical methods that use a rigid category-based representation, exemplar-based methods try to model variations among positives by learning from specific positive samples. However, current existing exemplar-based methods either fail to use any training information or suffer from a significant performance drop when few exemplars are available. In this paper, we design a novel local metric learning approach to well handle exemplar-based object detection task. The main works are two-fold: 1) a novel local metric learning algorithm called exemplar metric learning (EML) is designed and 2) an exemplar-based object detection algorithm based on EML is implemented. We evaluate our method on two generic object detection data sets: UIUC-Car and UMass FDDB. Experiments show that compared with other exemplar-based methods, our approach can effectively enhance object detection performance when few exemplars are available.
机译:对象检测已在计算机视觉社区中得到了广泛的研究,并且尽管有各种变化,例如比例,姿势,照明和背景,但它仍具有许多实际应用。大多数经典的对象检测方法严重依赖于基于类别的训练来处理类内变异。与使用基于分类的刚性表示法的经典方法相比,基于示例的方法尝试通过从特定阳性样本中学习来模拟阳性之间的差异。但是,当前现有的基于示例的方法要么无法使用任何训练信息,要么在几乎没有可用示例的情况下遭受严重的性能下降。在本文中,我们设计了一种新颖的局部度量学习方法,可以很好地处理基于示例的对象检测任务。主要工作有两个方面:1)设计了一种新颖的局部度量学习算法,称为范例度量学习(EML); 2)实现了一种基于范例的基于EML的目标检测算法。我们在两个通用的对象检测数据集上评估我们的方法:UIUC-Car和UMass FDDB。实验表明,与其他基于示例的方法相比,该方法在可用示例较少的情况下可以有效地提高目标检测性能。

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