sMoBYAL: supervised contrastive active learning for image classification

Thanh Hong Dang; Thanh Tung Nguyen; Huy Quang Trinh; Linh Bao Doan; Toan Van Pham

doi:10.1117/12.3023346

3 April 2024 sMoBYAL: supervised contrastive active learning for image classification

Thanh Hong Dang, Thanh Tung Nguyen, Huy Quang Trinh, Linh Bao Doan, Toan Van Pham

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 1307203 (2024) https://doi.org/10.1117/12.3023346
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

We propose a novel active learning framework for image classification - sMoBYAL. Our contribution is modifying MoBY - one of the highly effective self-supervised learning algorithms to utilize both labeled and unlabeled data for the active learning pipeline. Finally, we thoroughly evaluate and analyze the robustness and performance of our pipeline in image classification tasks. Our approach attains comparative outcomes, surpassing recent AL methods in terms of results. Our code available at: https://github.com/thanhdh-3030/sMoBYAL

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

Citation Download Citation

Thanh Hong Dang, Thanh Tung Nguyen, Huy Quang Trinh, Linh Bao Doan, and Toan Van Pham "sMoBYAL: supervised contrastive active learning for image classification", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 1307203 (3 April 2024); https://doi.org/10.1117/12.3023346

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