View in EDS HTML Full Text PDF Full Text

Canonical circuit computations for computer vision.

Saved in:
Bibliographic Details
Title: Canonical circuit computations for computer vision.
Authors: Schmid, Daniel1 (AUTHOR), Jarvers, Christian1 (AUTHOR), Neumann, Heiko1 (AUTHOR) heiko.neumann@uni-ulm.de
Source: Biological Cybernetics. Oct2023, Vol. 117 Issue 4/5, p299-329. 31p.
Subjects: Computer circuits, Visual perception, Computer engineering, Computer vision, Detectors
Abstract: Advanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advances in machine vision. We propose to utilize structural and functional principles of neural systems that have been largely overlooked. They potentially provide new inspirations for computer vision mechanisms and models. Recurrent feedforward, lateral, and feedback interactions characterize general principles underlying processing in mammals. We derive a formal specification of core computational motifs that utilize these principles. These are combined to define model mechanisms for visual shape and motion processing. We demonstrate how such a framework can be adopted to run on neuromorphic brain-inspired hardware platforms and can be extended to automatically adapt to environment statistics. We argue that the identified principles and their formalization inspires sophisticated computational mechanisms with improved explanatory scope. These and other elaborated, biologically inspired models can be employed to design computer vision solutions for different tasks and they can be used to advance neural network architectures of learning. [ABSTRACT FROM AUTHOR]
Copyright of Biological Cybernetics 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: 173179515
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Canonical circuit computations for computer vision.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Schmid%2C+Daniel%22">Schmid, Daniel</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jarvers%2C+Christian%22">Jarvers, Christian</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Neumann%2C+Heiko%22">Neumann, Heiko</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> heiko.neumann@uni-ulm.de</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Biological+Cybernetics%22">Biological Cybernetics</searchLink>. Oct2023, Vol. 117 Issue 4/5, p299-329. 31p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+circuits%22">Computer circuits</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+perception%22">Visual perception</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+engineering%22">Computer engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Detectors%22">Detectors</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Advanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advances in machine vision. We propose to utilize structural and functional principles of neural systems that have been largely overlooked. They potentially provide new inspirations for computer vision mechanisms and models. Recurrent feedforward, lateral, and feedback interactions characterize general principles underlying processing in mammals. We derive a formal specification of core computational motifs that utilize these principles. These are combined to define model mechanisms for visual shape and motion processing. We demonstrate how such a framework can be adopted to run on neuromorphic brain-inspired hardware platforms and can be extended to automatically adapt to environment statistics. We argue that the identified principles and their formalization inspires sophisticated computational mechanisms with improved explanatory scope. These and other elaborated, biologically inspired models can be employed to design computer vision solutions for different tasks and they can be used to advance neural network architectures of learning. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Biological Cybernetics 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=173179515
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00422-023-00966-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 31
        StartPage: 299
    Subjects:
      – SubjectFull: Computer circuits
        Type: general
      – SubjectFull: Visual perception
        Type: general
      – SubjectFull: Computer engineering
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Detectors
        Type: general
    Titles:
      – TitleFull: Canonical circuit computations for computer vision.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Schmid, Daniel
      – PersonEntity:
          Name:
            NameFull: Jarvers, Christian
      – PersonEntity:
          Name:
            NameFull: Neumann, Heiko
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 03401200
          Numbering:
            – Type: volume
              Value: 117
            – Type: issue
              Value: 4/5
          Titles:
            – TitleFull: Biological Cybernetics
              Type: main
ResultId 1