Naming conventions-based multi-label and multi-task learning for fine-grained classification

Qinbang Zhou; Kezhi Zhang; Feng Yue; Zhaoliang Zhang; Hui Yu

doi:10.1117/12.3014589

9 January 2024 Naming conventions-based multi-label and multi-task learning for fine-grained classification

Qinbang Zhou, Kezhi Zhang, Feng Yue, Zhaoliang Zhang, Hui Yu

Proceedings Volume 12969, International Conference on Algorithm, Imaging Processing, and Machine Vision (AIPMV 2023); 129691D (2024) https://doi.org/10.1117/12.3014589
Event: International Conference on Algorithm, Imaging Processing and Machine Vision (AIPMV 2023), 2023, Qingdao, China

Abstract

This paper proposes a fine-grained image classification architecture using multi-task learning. The structure of the fine-grained classification network uses ResNest as the feature extraction layer of the multi-task hard parameter sharing mode with the fine-grained category label regression branch based on multi-hot naming conventions and classification branch based on cross-entropy loss with one-hot encoding. The coupling between the two branches enables multi-task classification through hyperparameter weighting. Subsequently, comparison and ablation experiments were performed on the public datasets of Stanford Cars, CUB-200-2011 and FGVC-Aircraft. The experimental result shows multi-label regression, multi-task learning and label smoothing can effectively improve the generalization of the model and increase the inter-class distance of the previous layer at the network output terminal, and reduces the intra-class distance.

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

Citation Download Citation

Qinbang Zhou, Kezhi Zhang, Feng Yue, Zhaoliang Zhang, and Hui Yu "Naming conventions-based multi-label and multi-task learning for fine-grained classification", Proc. SPIE 12969, International Conference on Algorithm, Imaging Processing, and Machine Vision (AIPMV 2023), 129691D (9 January 2024); https://doi.org/10.1117/12.3014589

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