...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >Instance-level object retrieval via deep region CNN
【24h】

Instance-level object retrieval via deep region CNN

机译：通过深区域CNN检索实例级对象

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Instance retrieval is a fundamental problem in the multimedia field for its various applications. Since the relevancy is defined at the instance level, it is more challenging comparing to traditional image retrieval methods. Recent advances show that Convolutional Neural Networks (CNNs) offer an attractive method for image feature representations. However, the CNN method extracts features from the whole image, thus the extracted features contain a large amount of background noisy information, leading to poor retrieval performance. To solve the problem, this paper proposed a deep region CNN method with object detection for instance-level object retrieval, which has two phases, i.e., offline Faster R-CNN training and online instance retrieval. First, we train a Faster R-CNN model to better locate the region of the objects. Second, we extract the CNN features from the detected object image region and then retrieve relevant images based on the visual similarity of these features. Furthermore, we utilized three different strategies for feature fusing based on the detected object region candidates from Faster R-CNN. We conduct the experiment on a large dataset: INSTRE with 23,070 object images and additional one million distractor images. Qualitative and quantitative evaluation results have demonstrated the advantage of our proposed method. In addition, we conducted extensive experiments on the Oxford dataset and the experimental results further validated the effectiveness of our proposed method.
机译：实例检索是多媒体领域中各种应用程序的基本问题。由于相关性是在实例级别定义的，因此与传统的图像检索方法相比更具挑战性。最新进展表明，卷积神经网络（CNN）为图像特征表示提供了一种有吸引力的方法。然而，CNN方法从整个图像中提取特征，因此所提取的特征包含大量的背景噪声信息，导致检索性能较差。为了解决该问题，本文提出了一种用于实例级对象检索的带对象检测的深区域CNN方法，该方法分为离线Faster R-CNN训练和在线实例检索两个阶段。首先，我们训练了Faster R-CNN模型，以更好地定位对象区域。其次，我们从检测到的目标图像区域中提取CNN特征，然后根据这些特征的视觉相似性检索相关图像。此外，我们根据来自Faster R-CNN的检测到的候选对象区域，采用了三种不同的特征融合策略。我们在一个大型数据集上进行了实验：INSTRE具有23,070个对象图像和另外一百万个干扰项图像。定性和定量评估结果证明了我们提出的方法的优势。此外，我们对牛津数据集进行了广泛的实验，实验结果进一步验证了我们提出的方法的有效性。

著录项

  • 来源
    《Multimedia Tools and Applications》 |2019年第10期|13247-13261|共15页
  • 作者

    Mei Shuhuan; Min Weiqing; Duan Hua; Jiang Shuqiang;

  • 作者单位

    Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Shandong, Peoples R China|Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China;

    Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China;

    Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Shandong, Peoples R China;

    Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China|Univ Chinese Acad Sci, Beijing 100049, Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Faster R-CNN; Deep learning; Instance-level object retrieval; Instre;

    机译：更快的R-CNN;深度学习;实例级对象检索;Instre;

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