Object detection algorithm for handling sample imbalance problems based on dynamic weighted label assignment

Yi Yang; Hong Fan; ShuYu Yu; SuPing Yu; WuJun Xu

doi:10.1117/12.2681557

1 June 2023 Object detection algorithm for handling sample imbalance problems based on dynamic weighted label assignment

Yi Yang, Hong Fan, ShuYu Yu, SuPing Yu, WuJun Xu

Author Affiliations +

Proceedings Volume 12718, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023); 127180K (2023) https://doi.org/10.1117/12.2681557
Event: International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023), 2023, Nanjing, China

Abstract

The relatively large variation in samples from different categories in the object detection dataset leads to the problem of sample imbalance, which in turn affects the accuracy of the object detector. In this paper, a dynamically weighted approach to label assignment is proposed to enable model to suppress abnormal samples and mine hard samples during training, thus solving the problem of sample imbalance. Different dynamic weighting strategies are applied to positive and negative samples to calculate the classification loss, and a dynamically weighted EIOU method is used to calculate the localization loss. In addition, modifying the single convolutional prediction head to a dual prediction head structure enables the model to focus more on performing classification and regression tasks. This structure uses a fully-connected head to predict the classification results and a convolutional head to predict the localisation results. Experiments conducted on PASCAL VOC2007+12 show that the proposed method can help YOLOv5 to achieve better accuracy and reach 72.3 mAP in 100 epochs, an improvement of 2.4 mAP over the original model. Furthermore, we have done several experiments on MSCOCO to demonstrate the effectiveness of the proposed dynamic weighting method, which has implications for building faster and stronger object detectors.

Citation Download Citation

Yi Yang, Hong Fan, ShuYu Yu, SuPing Yu, and WuJun Xu "Object detection algorithm for handling sample imbalance problems based on dynamic weighted label assignment", Proc. SPIE 12718, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023), 127180K (1 June 2023); https://doi.org/10.1117/12.2681557

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Object detection

Head

Detection and tracking algorithms

Performance modeling

Deep learning

Design and modelling

Computer vision technology

Keywords/Phrases

Search In:

Publication Years