View in EDS PDF Full Text

Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings.

Saved in:
Bibliographic Details
Title: Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings.
Authors: Morgado, Pedro1 (AUTHOR) pmaravil@eng.ucsd.edu, Li, Yunsheng1 (AUTHOR), Costa Pereira, Jose2 (AUTHOR), Saberian, Mohammad3 (AUTHOR), Vasconcelos, Nuno1 (AUTHOR)
Source: International Journal of Computer Vision. Feb2021, Vol. 129 Issue 2, p419-438. 20p.
Subjects: Hashing, Convolutional neural networks, Proxy
Abstract: Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve good performance on both tasks, they are non-trivial to binarize, due to a rotational ambiguity that encourages non-binary embeddings. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both classification and hashing is introduced. The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error, while producing highly discriminative hash-codes. A semantic extension (sHCLM), aimed to improve hashing performance in a transfer scenario, is also proposed. Extensive experiments show that sHCLM embeddings achieve significant improvements over state-of-the-art hashing procedures on several small and large datasets, both within and beyond the set of training classes. [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
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 148703308
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Morgado%2C+Pedro%22">Morgado, Pedro</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> pmaravil@eng.ucsd.edu</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Yunsheng%22">Li, Yunsheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Costa+Pereira%2C+Jose%22">Costa Pereira, Jose</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Saberian%2C+Mohammad%22">Saberian, Mohammad</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vasconcelos%2C+Nuno%22">Vasconcelos, Nuno</searchLink><relatesTo>1</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>. Feb2021, Vol. 129 Issue 2, p419-438. 20p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Hashing%22">Hashing</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Proxy%22">Proxy</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve good performance on both tasks, they are non-trivial to binarize, due to a rotational ambiguity that encourages non-binary embeddings. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both classification and hashing is introduced. The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error, while producing highly discriminative hash-codes. A semantic extension (sHCLM), aimed to improve hashing performance in a transfer scenario, is also proposed. Extensive experiments show that sHCLM embeddings achieve significant improvements over state-of-the-art hashing procedures on several small and large datasets, both within and beyond the set of training classes. [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=148703308
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11263-020-01362-7
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 419
    Subjects:
      – SubjectFull: Hashing
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Proxy
        Type: general
    Titles:
      – TitleFull: Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Morgado, Pedro
      – PersonEntity:
          Name:
            NameFull: Li, Yunsheng
      – PersonEntity:
          Name:
            NameFull: Costa Pereira, Jose
      – PersonEntity:
          Name:
            NameFull: Saberian, Mohammad
      – PersonEntity:
          Name:
            NameFull: Vasconcelos, Nuno
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 09205691
          Numbering:
            – Type: volume
              Value: 129
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: International Journal of Computer Vision
              Type: main
ResultId 1