View in EDS

Graph Representation and Prototype Learning for webly supervised fine-grained image recognition.

Saved in:
Bibliographic Details
Title: Graph Representation and Prototype Learning for webly supervised fine-grained image recognition.
Authors: Lin, Jiantao1,2 (AUTHOR) jlin695@connect.hkust-gz.edu.cn, Chen, Tianshui1 (AUTHOR) chentianshui@gdut.edu.cn, Chen, Yingcong2 (AUTHOR) yingcongchen@ust.hk, Yang, Zhijing1 (AUTHOR) yzhj@gdut.edu.cn, Gao, YueFang3 (AUTHOR) gaoyuefang@scau.edu.cn
Source: Pattern Recognition Letters. Jul2024, Vol. 183, p78-85. 8p.
Subjects: Representations of graphs, Machine learning, Image recognition (Computer vision), Supervised learning, Prototypes, Holistic education
Abstract: Webly supervised fine-grained image recognition (FGIR) learns to distinguish sub-ordinate categories based on webly-retrieved data, which can dramatically alleviate the dependency on manually annotated labels. This is quite a challenging task due to the heavy noise labels and the inherent dilemma of small inter-class variance and large intra-class variance. Current webly supervised algorithms learn holistic category prototypes to help correct noisy labels but ignore local features that can distinguish different sub-ordinate categories. In this work, we propose a Graph Representation and Prototype Learning (GRPL) framework to automatically mine discriminative local regions and their interactions with holistic image to learn instance graph representation both category graph prototype to help correct noisy labels and retrieve out-of-distribution (OOD) samples. Specifically, an attention-focused module is designed to extract the discriminative regions and then build a structured graph to correlate them with the holistic image for each instance and an identical graph to model holistic-local correlations for each category. Next, we apply two stacked graph convolution networks to explore holistic-local interaction within each graph and across two graphs to learn graph representation for each instance and graph prototype for each category. Finally, the similarities between the instance-level and prototype-level graph representation are learned to help correct noisy labels and exclude OOD samples. Extensive experiments conducted on several datasets show the proposed approach achieves superior performance compared with current leading algorithms. • Framework learning graph-level similarity for webly supervised fine-grained image recognition. • Unified strategy to identify and correct noisy labels. • Superior performance across multiple datasets. [ABSTRACT FROM AUTHOR]
Copyright of Pattern Recognition Letters is the property of Elsevier B.V. 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 Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 177885639
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Graph Representation and Prototype Learning for webly supervised fine-grained image recognition.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lin%2C+Jiantao%22">Lin, Jiantao</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> jlin695@connect.hkust-gz.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Tianshui%22">Chen, Tianshui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> chentianshui@gdut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Yingcong%22">Chen, Yingcong</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> yingcongchen@ust.hk</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Zhijing%22">Yang, Zhijing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yzhj@gdut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Gao%2C+YueFang%22">Gao, YueFang</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> gaoyuefang@scau.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Pattern+Recognition+Letters%22">Pattern Recognition Letters</searchLink>. Jul2024, Vol. 183, p78-85. 8p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Representations+of+graphs%22">Representations of graphs</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Image+recognition+%28Computer+vision%29%22">Image recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Supervised+learning%22">Supervised learning</searchLink><br /><searchLink fieldCode="DE" term="%22Prototypes%22">Prototypes</searchLink><br /><searchLink fieldCode="DE" term="%22Holistic+education%22">Holistic education</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Webly supervised fine-grained image recognition (FGIR) learns to distinguish sub-ordinate categories based on webly-retrieved data, which can dramatically alleviate the dependency on manually annotated labels. This is quite a challenging task due to the heavy noise labels and the inherent dilemma of small inter-class variance and large intra-class variance. Current webly supervised algorithms learn holistic category prototypes to help correct noisy labels but ignore local features that can distinguish different sub-ordinate categories. In this work, we propose a Graph Representation and Prototype Learning (GRPL) framework to automatically mine discriminative local regions and their interactions with holistic image to learn instance graph representation both category graph prototype to help correct noisy labels and retrieve out-of-distribution (OOD) samples. Specifically, an attention-focused module is designed to extract the discriminative regions and then build a structured graph to correlate them with the holistic image for each instance and an identical graph to model holistic-local correlations for each category. Next, we apply two stacked graph convolution networks to explore holistic-local interaction within each graph and across two graphs to learn graph representation for each instance and graph prototype for each category. Finally, the similarities between the instance-level and prototype-level graph representation are learned to help correct noisy labels and exclude OOD samples. Extensive experiments conducted on several datasets show the proposed approach achieves superior performance compared with current leading algorithms. • Framework learning graph-level similarity for webly supervised fine-grained image recognition. • Unified strategy to identify and correct noisy labels. • Superior performance across multiple datasets. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Pattern Recognition Letters is the property of Elsevier B.V. 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=177885639
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.patrec.2024.05.002
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 78
    Subjects:
      – SubjectFull: Representations of graphs
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Image recognition (Computer vision)
        Type: general
      – SubjectFull: Supervised learning
        Type: general
      – SubjectFull: Prototypes
        Type: general
      – SubjectFull: Holistic education
        Type: general
    Titles:
      – TitleFull: Graph Representation and Prototype Learning for webly supervised fine-grained image recognition.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lin, Jiantao
      – PersonEntity:
          Name:
            NameFull: Chen, Tianshui
      – PersonEntity:
          Name:
            NameFull: Chen, Yingcong
      – PersonEntity:
          Name:
            NameFull: Yang, Zhijing
      – PersonEntity:
          Name:
            NameFull: Gao, YueFang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 01678655
          Numbering:
            – Type: volume
              Value: 183
          Titles:
            – TitleFull: Pattern Recognition Letters
              Type: main
ResultId 1