View in EDS

Blind Image Quality Assessment for Authentic Distortions by Intermediary Enhancement and Iterative Training.

Saved in:
Bibliographic Details
Title: Blind Image Quality Assessment for Authentic Distortions by Intermediary Enhancement and Iterative Training.
Authors: Song, Tianshu1 tianshusong@cumt.edu.cn, Li, Leida2 ldli@xidian.edu.cn, Chen, Pengfei2 cpf00790079@gmail.com, Liu, Hantao3 hantao.liu@cs.cardiff.ac.uk, Qian, Jiansheng3 qianjsh@cumt.edu.cn
Source: IEEE Transactions on Circuits & Systems for Video Technology. Nov2022, Vol. 32 Issue 11, p7592-7604. 13p.
Subjects: Image quality analysis, Artificial neural networks, Authentic assessment, Feature extraction, Transfer of training, Knowledge transfer
Abstract: With the boom of deep neural networks, blind image quality assessment (BIQA) has achieved great processes. However, the current BIQA metrics are limited when evaluating low-quality images as compared to medium-quality and high-quality images, which restricts their applications in real world problems. In this paper, we first identify that two challenges caused by distribution shift and long-tailed distribution lead to the compromised performance on low-quality images. Then, we propose an intermediary enhancement-based bilateral network with iterative training strategy for solving these two challenges. Drawing on the experience of transitive transfer learning, the proposed metric adaptively introduces enhanced intermediary images to transfer more information to low-quality images for mitigating the distribution shift. Our metric also adopts an iterative training strategy to deal with the long-tailed distribution. This strategy decouples feature extraction and score regression for better representation learning and regressor training. It not only transfers the knowledge learned from the earlier stage to the latter stage, but also makes the model pay more attention to long-tailed low-quality images. We conduct extensive experiments on five authentically distorted image quality datasets. The results show that our metric significantly improves the evaluating performance on low-quality images and delivers state-of-the-art intra-dataset results. During generalization tests, our metric also achieves the best cross-dataset performance. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Circuits & Systems for Video Technology is the property of IEEE 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: 160691239
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Blind Image Quality Assessment for Authentic Distortions by Intermediary Enhancement and Iterative Training.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Song%2C+Tianshu%22">Song, Tianshu</searchLink><relatesTo>1</relatesTo><i> tianshusong@cumt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Leida%22">Li, Leida</searchLink><relatesTo>2</relatesTo><i> ldli@xidian.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Pengfei%22">Chen, Pengfei</searchLink><relatesTo>2</relatesTo><i> cpf00790079@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Hantao%22">Liu, Hantao</searchLink><relatesTo>3</relatesTo><i> hantao.liu@cs.cardiff.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Qian%2C+Jiansheng%22">Qian, Jiansheng</searchLink><relatesTo>3</relatesTo><i> qianjsh@cumt.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Circuits+%26+Systems+for+Video+Technology%22">IEEE Transactions on Circuits & Systems for Video Technology</searchLink>. Nov2022, Vol. 32 Issue 11, p7592-7604. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+quality+analysis%22">Image quality analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Authentic+assessment%22">Authentic assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Transfer+of+training%22">Transfer of training</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+transfer%22">Knowledge transfer</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: With the boom of deep neural networks, blind image quality assessment (BIQA) has achieved great processes. However, the current BIQA metrics are limited when evaluating low-quality images as compared to medium-quality and high-quality images, which restricts their applications in real world problems. In this paper, we first identify that two challenges caused by distribution shift and long-tailed distribution lead to the compromised performance on low-quality images. Then, we propose an intermediary enhancement-based bilateral network with iterative training strategy for solving these two challenges. Drawing on the experience of transitive transfer learning, the proposed metric adaptively introduces enhanced intermediary images to transfer more information to low-quality images for mitigating the distribution shift. Our metric also adopts an iterative training strategy to deal with the long-tailed distribution. This strategy decouples feature extraction and score regression for better representation learning and regressor training. It not only transfers the knowledge learned from the earlier stage to the latter stage, but also makes the model pay more attention to long-tailed low-quality images. We conduct extensive experiments on five authentically distorted image quality datasets. The results show that our metric significantly improves the evaluating performance on low-quality images and delivers state-of-the-art intra-dataset results. During generalization tests, our metric also achieves the best cross-dataset performance. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Circuits & Systems for Video Technology is the property of IEEE 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=160691239
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TCSVT.2022.3179744
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 7592
    Subjects:
      – SubjectFull: Image quality analysis
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Authentic assessment
        Type: general
      – SubjectFull: Feature extraction
        Type: general
      – SubjectFull: Transfer of training
        Type: general
      – SubjectFull: Knowledge transfer
        Type: general
    Titles:
      – TitleFull: Blind Image Quality Assessment for Authentic Distortions by Intermediary Enhancement and Iterative Training.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Song, Tianshu
      – PersonEntity:
          Name:
            NameFull: Li, Leida
      – PersonEntity:
          Name:
            NameFull: Chen, Pengfei
      – PersonEntity:
          Name:
            NameFull: Liu, Hantao
      – PersonEntity:
          Name:
            NameFull: Qian, Jiansheng
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 10518215
          Numbering:
            – Type: volume
              Value: 32
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: IEEE Transactions on Circuits & Systems for Video Technology
              Type: main
ResultId 1