...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >Asymmetric Binary Coding for Image Search
【24h】

Asymmetric Binary Coding for Image Search

机译：用于图像搜索的非对称二进制编码

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

Learning to hash has attracted broad research interests in recent computer vision and machine learning studies, due to its ability to accomplish efficient approximate nearest neighbor search. However, the closely related task, maximum inner product search (MIPS), has rarely been studied in this literature. To facilitate the MIPS study, in this paper, we introduce a general binary coding framework based on asymmetric hash functions, named asymmetric inner-product binary coding (AIBC). In particular, AIBC learns two different hash functions, which can reveal the inner products between original data vectors by the generated binary vectors. Although conceptually simple, the associated optimization is very challenging due to the highly nonsmooth nature of the objective that involves sign functions. We tackle the nonsmooth optimization in an alternating manner, by which each single coding function is optimized in an efficient discrete manner. We also simplify the objective by discarding the quadratic regularization term which significantly boosts the learning efficiency. Both problems are optimized in an effective discrete way without continuous relaxations, which produces high-quality hash codes. In addition, we extend the AIBC approach to the supervised hashing scenario, where the inner products of learned binary codes are forced to fit the supervised similarities. Extensive experiments on several benchmark image retrieval databases validate the superiority of the AIBC approaches over many recently proposed hashing algorithms.
机译：由于其能够完成有效的近似最近邻居搜索的能力，因此在最近的计算机视觉和机器学习研究中，哈希学习引起了广泛的研究兴趣。但是，在这个文献中很少研究与之密切相关的任务，即最大内积搜索（MIPS）。为了促进MIPS研究，在本文中，我们介绍了一个基于非对称哈希函数的通用二进制编码框架，称为非对称内积二进制编码（AIBC）。特别是，AIBC学习了两个不同的哈希函数，它们可以通过生成的二进制向量揭示原始数据向量之间的内积。尽管从概念上讲很简单，但是由于涉及符号功能的物镜的高度不平滑特性，相关的优化仍然非常具有挑战性。我们以交替的方式解决非平滑优化问题，通过这种方式，每个单个编码功能都以有效的离散方式进行了优化。我们还通过丢弃二次正则项来简化目标，从而显着提高学习效率。这两个问题都以有效的离散方式进行了优化，而没有连续的松弛，从而产生了高质量的哈希码。此外，我们将AIBC方法扩展到有监督的哈希方案，在该方案中，学习到的二进制代码的内积被迫适应有监督的相似性。在几个基准图像检索数据库上进行的大量实验证明了AIBC方法优于许多最近提出的哈希算法。

著录项

  • 来源
    《IEEE transactions on multimedia》 |2017年第9期|2022-2032|共11页
  • 作者

    Fumin Shen; Yang Yang; Li Liu; Wei Liu; Dacheng Tao; Heng Tao Shen;

  • 作者单位

    Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;

    Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;

    Malong Technologies Company, Ltd., Shenzhen, China;

    Tencent AI Laboratory, Shenzhen, China;

    School of Information Technologies, University of Sydney, Sydney, NSW, Australia;

    Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China;

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

    Binary codes; Encoding; Optimization; Kernel; Image coding; Databases; Standards;

    机译：二进制码;编码;优化;内核;图像编码;数据库;标准;

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