View in EDS PDF Full Text

MINIMUM FIDELITY FOR RELIABLE ARCHITECTURE RANKING IN BAYESIAN NAS FOR OBJECT DETECTION.

Saved in:
Bibliographic Details
Title: MINIMUM FIDELITY FOR RELIABLE ARCHITECTURE RANKING IN BAYESIAN NAS FOR OBJECT DETECTION.
Alternate Title: Мінімальна точність для надійного рейтингу архітектури в баєсівському NAS для виявлення об’єктів.
Authors: Kot, Anatoly1 anatoly.kot@gmail.com
Source: Electronics & Control Systems. 2026, Vol. 88 Issue 2, p54-60. 7p.
Subjects: Neural architecture search, Rank correlation (Statistics), Mathematical optimization, Object recognition (Computer vision), Computer performance
Abstract: This paper addresses the problem of reducing computational costs in Neural Architecture Search for object detection. The key question in low-fidelity approaches is: after what minimum number of epochs does the early training signal already provide acceptable architecture ranking? This paper presents a methodology for determining minimum fidelity based on out-of-sample rank correlation: trials are split into calibration (70%) and test (30%) sets, a composite proxy is built on the first set and evaluated on the second. An empirical study was conducted on 60 architectures trained for 25 epochs on an object detection dataset (6,772 images, 6 classes). The results show that a rank ensemble of three training metrics (val_loss, train_accuracy, val_accuracy) achieves Spearman ρ = 0.877 out-of-sample at epoch 3, providing 88% computational savings. A more complex 7-component metric underperforms the simple ensemble due to overfitting on a small sample (ρ_test = 0.70 vs. 0.88). The results are locally valid within the studied search space and the specific dataset. [ABSTRACT FROM AUTHOR]
Copyright of Electronics & Control Systems is the property of National Aviation University 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: 193870785
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: MINIMUM FIDELITY FOR RELIABLE ARCHITECTURE RANKING IN BAYESIAN NAS FOR OBJECT DETECTION.
– Name: TitleAlt
  Label: Alternate Title
  Group: TiAlt
  Data: Мінімальна точність для надійного рейтингу архітектури в баєсівському NAS для виявлення об’єктів.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kot%2C+Anatoly%22">Kot, Anatoly</searchLink><relatesTo>1</relatesTo><i> anatoly.kot@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Electronics+%26+Control+Systems%22">Electronics & Control Systems</searchLink>. 2026, Vol. 88 Issue 2, p54-60. 7p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Neural+architecture+search%22">Neural architecture search</searchLink><br /><searchLink fieldCode="DE" term="%22Rank+correlation+%28Statistics%29%22">Rank correlation (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+performance%22">Computer performance</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper addresses the problem of reducing computational costs in Neural Architecture Search for object detection. The key question in low-fidelity approaches is: after what minimum number of epochs does the early training signal already provide acceptable architecture ranking? This paper presents a methodology for determining minimum fidelity based on out-of-sample rank correlation: trials are split into calibration (70%) and test (30%) sets, a composite proxy is built on the first set and evaluated on the second. An empirical study was conducted on 60 architectures trained for 25 epochs on an object detection dataset (6,772 images, 6 classes). The results show that a rank ensemble of three training metrics (val_loss, train_accuracy, val_accuracy) achieves Spearman ρ = 0.877 out-of-sample at epoch 3, providing 88% computational savings. A more complex 7-component metric underperforms the simple ensemble due to overfitting on a small sample (ρ_test = 0.70 vs. 0.88). The results are locally valid within the studied search space and the specific dataset. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Electronics & Control Systems is the property of National Aviation University 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=193870785
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.18372/1990-5548.88.20966
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 7
        StartPage: 54
    Subjects:
      – SubjectFull: Neural architecture search
        Type: general
      – SubjectFull: Rank correlation (Statistics)
        Type: general
      – SubjectFull: Mathematical optimization
        Type: general
      – SubjectFull: Object recognition (Computer vision)
        Type: general
      – SubjectFull: Computer performance
        Type: general
    Titles:
      – TitleFull: MINIMUM FIDELITY FOR RELIABLE ARCHITECTURE RANKING IN BAYESIAN NAS FOR OBJECT DETECTION.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kot, Anatoly
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: 2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19905548
          Numbering:
            – Type: volume
              Value: 88
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Electronics & Control Systems
              Type: main
ResultId 1