Neural Prompt Search
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5268-5280
DOI: 10.1109/tpami.2024.3435939 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Yuanhan Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Ministry of Education - Singapore, Hong Kong Research Grants Council Early Career Scheme.
Abstract (Originalsprache)
The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-efficient tuning methods, such as learning adapter layers or visual prompt tokens, which allow a tiny portion of model parameters to be trained whereas the vast majority obtained from pre-training are frozen. However, designing a proper tuning method is non-trivial: one might need to try out a lengthy list of design choices, not to mention that each downstream dataset often requires custom designs. In this paper, we view the existing parameter-efficient tuning methods as "prompt modules" and propose Neural prOmpt seArcH (NOAH), a novel approach that learns, for large vision models, the optimal design of prompt modules through a neural architecture search algorithm, specifically for each downstream dataset. By conducting extensive experiments on over 20 vision datasets, we demonstrate that NOAH (i) is superior to individual prompt modules, (ii) has good few-shot learning ability, and (iii) is domain-generalizable.
Förderung
- Ministry of Education - Singapore
- Hong Kong Research Grants Council Early Career Scheme
Zitieren
APA
Zhang, Y., Zhou, K., & Liu, Z. (2025). Neural Prompt Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5268-5280. https://doi.org/10.1109/tpami.2024.3435939
Vancouver
Zhang Y, Zhou K, Liu Z. Neural Prompt Search. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5268-5280. doi:10.1109/tpami.2024.3435939
BibTeX
@article{Zhang2025,
author = {Zhang, Yuanhan and Zhou, Kaiyang and Liu, Ziwei},
title = {Neural Prompt Search},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {7},
pages = {5268--5280},
doi = {10.1109/tpami.2024.3435939}
}
EUVIMED