View in EDS HTML Full Text PDF Full Text

A General Framework for Deep Supervised Discrete Hashing.

Saved in:
Bibliographic Details
Title: A General Framework for Deep Supervised Discrete Hashing.
Authors: Li, Qi1,2,3 (AUTHOR), Sun, Zhenan1,3,4 (AUTHOR) znsun@nlpr.ia.ac.cn, He, Ran1,3,4 (AUTHOR), Tan, Tieniu1,3,4 (AUTHOR)
Source: International Journal of Computer Vision. Sep2020, Vol. 128 Issue 8/9, p2204-2222. 19p. 1 Diagram, 10 Charts, 6 Graphs.
Subjects: Hashing, Streaming video & television, Binary codes, Deep learning, Cost functions, Video compression
Abstract: With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefiting from recent advances in deep learning, deep hashing methods have shown superior performance over the traditional hashing methods. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a general deep supervised discrete hashing framework based on the assumption that the learned binary codes should be ideal for classification. Both the similarity information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithms. Besides, both the pairwise similarity information and the triplet ranking information are exploited in this paper. In addition, two different loss functions are presented: l 2 loss and hinge loss, which are carefully designed for the classification term under the one stream framework. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our approach outperforms current state-of-the-art methods on benchmark datasets. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 145079272
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A General Framework for Deep Supervised Discrete Hashing.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Li%2C+Qi%22">Li, Qi</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Zhenan%22">Sun, Zhenan</searchLink><relatesTo>1,3,4</relatesTo> (AUTHOR)<i> znsun@nlpr.ia.ac.cn</i><br /><searchLink fieldCode="AR" term="%22He%2C+Ran%22">He, Ran</searchLink><relatesTo>1,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tan%2C+Tieniu%22">Tan, Tieniu</searchLink><relatesTo>1,3,4</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Sep2020, Vol. 128 Issue 8/9, p2204-2222. 19p. 1 Diagram, 10 Charts, 6 Graphs.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Hashing%22">Hashing</searchLink><br /><searchLink fieldCode="DE" term="%22Streaming+video+%26+television%22">Streaming video & television</searchLink><br /><searchLink fieldCode="DE" term="%22Binary+codes%22">Binary codes</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Cost+functions%22">Cost functions</searchLink><br /><searchLink fieldCode="DE" term="%22Video+compression%22">Video compression</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years. Benefiting from recent advances in deep learning, deep hashing methods have shown superior performance over the traditional hashing methods. However, there are some limitations of previous deep hashing methods (e.g., the semantic information is not fully exploited). In this paper, we develop a general deep supervised discrete hashing framework based on the assumption that the learned binary codes should be ideal for classification. Both the similarity information and the classification information are used to learn the hash codes within one stream framework. We constrain the outputs of the last layer to be binary codes directly, which is rarely investigated in deep hashing algorithms. Besides, both the pairwise similarity information and the triplet ranking information are exploited in this paper. In addition, two different loss functions are presented: l 2 loss and hinge loss, which are carefully designed for the classification term under the one stream framework. Because of the discrete nature of hash codes, an alternating minimization method is used to optimize the objective function. Experimental results have shown that our approach outperforms current state-of-the-art methods on benchmark datasets. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=145079272
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-020-01327-w
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 2204
    Subjects:
      – SubjectFull: Hashing
        Type: general
      – SubjectFull: Streaming video & television
        Type: general
      – SubjectFull: Binary codes
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Cost functions
        Type: general
      – SubjectFull: Video compression
        Type: general
    Titles:
      – TitleFull: A General Framework for Deep Supervised Discrete Hashing.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Qi
      – PersonEntity:
          Name:
            NameFull: Sun, Zhenan
      – PersonEntity:
          Name:
            NameFull: He, Ran
      – PersonEntity:
          Name:
            NameFull: Tan, Tieniu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2020
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 128
            – Type: issue
              Value: 8/9
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1