Test-time Specialization of Dynamic Neural Networks

Sam Leroux*, Dewant Katare, Aaron Yi Ding, Pieter Simoens

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

20 Downloads (Pure)

Abstract

In recent years, there has been a notable increase in the size of commonly used image classification models. This growth has empowered models to recognize thousands of diverse object types. However, their computational demands pose significant challenges, especially when deploying them on resource-constrained edge devices. In many use cases where a model is deployed on an edge device, only a small subset of the classes will ever be observed by a given model instance. Our proposed test-time specialization of dynamic neural networks allows these models to become faster at recognizing the classes that are observed frequently, while maintaining the ability to recognize all other classes, albeit slightly less efficient. We benchmark our approach on a real-world edge device, obtaining significant speedups compared to the baseline model without test-time adaptation.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
PublisherIEEE
Pages1048-1056
Number of pages9
ISBN (Electronic)9798350365474
DOIs
Publication statusPublished - 2024
Event2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 - Seattle, United States
Duration: 16 Jun 202422 Jun 2024

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
Country/TerritoryUnited States
CitySeattle
Period16/06/2422/06/24

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Edge AI
  • resource efficient deep learning
  • Test time adaptation

Fingerprint

Dive into the research topics of 'Test-time Specialization of Dynamic Neural Networks'. Together they form a unique fingerprint.

Cite this