ub.xmlui.mirage2.page-structure.muninLogoub.xmlui.mirage2.page-structure.openResearchArchiveLogo
    • EnglishEnglish
    • norsknorsk
  • Velg spraakEnglish 
    • EnglishEnglish
    • norsknorsk
  • Administration/UB
View Item 
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for informatikk
  • Artikler, rapporter og annet (informatikk)
  • View Item
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for informatikk
  • Artikler, rapporter og annet (informatikk)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Customizable and Programmable Deep Learning

Permanent link
https://hdl.handle.net/10037/36964
DOI
https://doi.org/10.1007/978-3-031-78107-0_7
Thumbnail
View/Open
article.pdf (711.8Kb)
Accepted manuscript version (PDF)
Date
2024-12-02
Type
Conference object
Konferansebidrag

Author
Pal, Ratnabali; Sekh, Arif Ahmed
Abstract
In this study, we explore the potential of pre-trained deep learning models, proposing a new approach that emphasizes their reusability and adaptability. Our framework, termed “customizable” deep learning, facilities users to seamlessly integrate diverse pre-trained models for addressing new tasks and enhancing existing solutions. Furthermore, we introduce a “programmable” adapter that enables the flexible combination of different pre-trained modules, expanding the range of applications and customization options. Through empirical experiments, particularly focusing on Visual Question Answering (VQA) for visually impaired (VI) individuals, we demonstrate the practical effectiveness of our methodology. These contributions advance the deep learning field while promoting customization and re-usability across various domains and tasks. The code is available https://github.com/Ratnabali-Pal/CPDA-VQA.
Publisher
Springer Nature
Series
Lecture Notes in Computer Science (LNCS) ; null
Citation
Pal, R., Kar, S., Sekh, A.A. (2025). Customizable and Programmable Deep Learning. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds) Pattern Recognition. ICPR 2024. Lecture Notes in Computer Science, vol 15301. Springer, Cham. https://doi.org/10.1007/978-3-031-78107-0_7
Metadata
Show full item record
Collections
  • Artikler, rapporter og annet (informatikk) [478]
Copyright 2024 The Author(s)

Browse

Browse all of MuninCommunities & CollectionsAuthor listTitlesBy Issue DateBrowse this CollectionAuthor listTitlesBy Issue Date
Login

Statistics

View Usage Statistics
UiT

Munin is powered by DSpace

UiT The Arctic University of Norway
The University Library
uit.no/ub - munin@ub.uit.no

Accessibility statement (Norwegian only)