...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval
【24h】

Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval

机译：不完整数据学习的迭代流形嵌入层用于大规模图像检索

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

Existing manifold learning methods are not appropriate for image retrieval tasks, because most of them are unable to process query images and they have much greater computational cost especially for large-scale database. Therefore, we propose the iterative manifold embedding (IME) layer, of which the weights are learned offline by an unsupervised strategy, to explore the intrinsic manifolds by incomplete data. On the large-scale database that contains 27 000 images, the IME layer is more than 120 times faster than other manifold learning methods to embed the original representations at query time. We embed the original descriptors of database images that lie on manifold in a high-dimensional space into manifold-based representations iteratively to generate the IME representations in an offline learning stage. According to the original descriptors and the IME representations of database images, we estimate the weights of the IME layer by ridge regression. In the online retrieval stage, we employ the IME layer to map the original representation of a query image with an ignorable time cost (2 ms per image). We experiment on five public standard datasets for image retrieval. The proposed IME layer significantly outperforms the related dimension reduction methods and manifold learning methods. Without postprocessing, our IME layer achieves a boost in the performance of state-of-the-art image retrieval methods with postprocessing on most datasets, and needs less computational cost.
机译：现有的多种学习方法不适用于图像检索任务，因为它们大多数无法处理查询图像，并且它们具有更大的计算成本，尤其是对于大型数据库。因此，我们提出了一种迭代流形嵌入（IME）层，其权重是通过无监督策略离线学习的，以利用不完整的数据来探索固有流形。在包含27000张图像的大型数据库上，IME层比其他在查询时嵌入原始表示的流形学习方法快120倍以上。我们将高维空间中流形上的数据库图像的原始描述符迭代地嵌入基于流形的表示中，以在离线学习阶段生成IME表示。根据原始描述符和数据库图像的IME表示，我们通过岭回归估计IME层的权重。在在线检索阶段，我们使用IME层以可忽略的时间成本（每个图像2毫秒）来映射查询图像的原始表示。我们对五个公共标准数据集进行了图像检索实验。提议的IME层明显优于相关的降维方法和流形学习方法。无需后处理，我们的IME层就可以对大多数数据集进行后处理，从而提高了最新图像检索方法的性能，并减少了计算成本。

著录项

  • 来源
    《IEEE transactions on multimedia》 |2019年第6期|1551-1562|共12页
  • 作者

    Xu Jian; Wang Chunheng; Qi Chengzuo; Shi Cunzhao; Xiao Baihua;

  • 作者单位

    Univ Chinese Acad Sci, Beijing 100190, Peoples R China|Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China;

    Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China;

    Univ Chinese Acad Sci, Beijing 100190, Peoples R China|Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China;

    Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China;

    Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China;

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

    Iterative manifold embedding layer; image retrieval; incomplete data;

    机译：迭代歧管嵌入层;图像检索;数据不完整;

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