EdgeVisionBench: A Benchmark of Evolving Input Domains for Vision Applications at Edge

Qinglong Zhang, Rui Han*, Chi Harold Liu, Guoren Wang, Lydia Y. Chen

*Corresponding author for this work

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

22 Downloads (Pure)

Abstract

Vision applications powered by deep neural networks (DNNs) are widely deployed on edge devices and solve the learning tasks of incoming data streams whose class label and input feature continuously evolve, known as domain shift. Despite its prominent presence in real-world edge scenarios, existing benchmarks used by domain adaptation methods overlook evolving domains and under represent their shifts in label and feature distributions. To address this gap, we present EdgeVisionBench, a benchmark seeking to generate evolving domains of various types and reflect their realistic label and feature shifts encountered by edge-based vision applications. To facilitate evaluating domain adaptation methods on edge devices, we provide an open-source package that automates workload generation, contains popular DNN models and compression techniques, and standardizes evaluations with interactive interfaces. Code and datasets are available at https://github.com/LINC-BIT/EdgeVisionBench.

Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023
Place of PublicationPiscataway
PublisherIEEE
Pages3643-3646
Number of pages4
ISBN (Electronic)979-8-3503-2227-9
ISBN (Print)979-8-3503-2228-6
DOIs
Publication statusPublished - 2023
Event39th IEEE International Conference on Data Engineering, ICDE 2023 - Anaheim, United States
Duration: 3 Apr 20237 Apr 2023

Publication series

NameProceedings - International Conference on Data Engineering
Volume2023-April
ISSN (Print)1084-4627

Conference

Conference39th IEEE International Conference on Data Engineering, ICDE 2023
Country/TerritoryUnited States
CityAnaheim
Period3/04/237/04/23

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

  • benchmark
  • Edge computing
  • evolving domains
  • vision applications

Fingerprint

Dive into the research topics of 'EdgeVisionBench: A Benchmark of Evolving Input Domains for Vision Applications at Edge'. Together they form a unique fingerprint.

Cite this