kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Applicability of Detection Transformers in Resource-Constrained Environments: Investigating Detection Transformer Performance Under Computational Limitations and Scarcity of Annotated Data
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Object detection is a fundamental task in computer vision, with significant applications in various domains. However, the reliance on large-scale annotated data and computational resource demands poses challenges in practical implementation. This thesis aims to address these complexities by exploring self-supervised training approaches for the detection transformer(DETR) family of object detectors. The project investigates the necessity of training the backbone under a semi-supervised setting and explores the benefits of initializing scene graph generation architectures with pretrained DETReg and DETR models for faster training convergence and reduced computational resource requirements. The significance of this research lies in the potential to mitigate the dependence on annotated data and make deep learning techniques more accessible to researchers and practitioners. By overcoming the limitations of data and computational resources, this thesis contributes to the accessibility of DETR and encourages a more sustainable and inclusive approach to deep learning research.

Abstract [sv]

Objektigenkänning är en grundläggande uppgift inom datorseende, med betydande tillämpningar inom olika domäner. Dock skapar beroendet av storskaliga annoterade data och krav på datorkraft utmaningar i praktisk implementering. Denna avhandling syftar till att ta itu med dessa komplexiteter genom att utforska självövervakade utbildningsmetoder för detektions transformer (DETR) familjen av objektdetektorer. Projektet undersöker nödvändigheten av att träna ryggraden under en semi-övervakad inställning och utforskar fördelarna med att initiera scenegrafgenereringsarkitekturer med förtränade DETReg-modeller för snabbare konvergens av träning och minskade krav på datorkraft. Betydelsen av denna forskning ligger i potentialen att mildra beroendet av annoterade data och göra djupinlärningstekniker mer tillgängliga för forskare och utövare. Genom att övervinna begränsningarna av data och datorkraft, bidrar denna avhandling till tillgängligheten av DETR och uppmuntrar till en mer hållbar och inkluderande inställning till djupinlärning forskning.

Place, publisher, year, edition, pages
2023. , p. 66
Series
TRITA-EECS-EX ; 2023:809
Keywords [en]
Deep Learning, Computer Vision, Self-supervised Learning, Object Detection, Scene Graph Generation
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-341883OAI: oai:DiVA.org:kth-341883DiVA, id: diva2:1824011
External cooperation
Abios Gaming AB
Supervisors
Examiners
Available from: 2024-02-02 Created: 2024-01-03 Last updated: 2024-02-02Bibliographically approved

Open Access in DiVA

fulltext(1904 kB)192 downloads
File information
File name FULLTEXT01.pdfFile size 1904 kBChecksum SHA-512
a504ce004ef906e8f5102b901e0e1bb0b278fe038bd51c2f7d43502d5694f2c35c4f13fad7ab5af928a2d0f7ef07040ef177c804aa8f0bd9f18f567260cacb03
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 192 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 310 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf