Vision language distillation by clustering bitrajectory matching

Jiaming Zhou; Shangjiaqi Hao; Qinghao Zhang

doi:10.1117/12.3037820

12 September 2024 Vision language distillation by clustering bitrajectory matching

Jiaming Zhou, Shangjiaqi Hao, Qinghao Zhang

Proceedings Volume 13256, Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024); 1325605 (2024) https://doi.org/10.1117/12.3037820
Event: Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024), 2024, Anshan, China

Abstract

Dataset distillation is often used to create compact datasets that can be used to achieve similar training performance, making it a good choice for addressing the challenges of data storage cost and training cost. However, existing distillation method are generally time-intensive and computationally expensive, especially when applied to vision-language tasks. To address this challenge, we propose the Clustering BiTrajectory Matching method, which accelerates existing distillation techniques by 8 times through two innovative strategies: a clustering-based sample selection and a biTrajectory optimization approach. The Clustering BiTrajectory Matching method can achieve good accuracy in a multi-modal setting while requiring lower computation resources and emphasizing efficiency in pre-training. We evaluate the proposed method on the Flickr8k dataset. We show that our method is able to achieve better efficiency (less iteration to achieve target accuracy), while outperforming other coreset selection methods.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jiaming Zhou, Shangjiaqi Hao, and Qinghao Zhang "Vision language distillation by clustering bitrajectory matching", Proc. SPIE 13256, Fourth International Conference on Computer Vision and Pattern Analysis (ICCPA 2024), 1325605 (12 September 2024); https://doi.org/10.1117/12.3037820

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available