Few-shot object detection via query feature calibration

Zhoufeng Liu; Xinnan Shao; Ertong Li

doi:10.1117/12.3057934

13 February 2025 Few-shot object detection via query feature calibration

Zhoufeng Liu, Xinnan Shao, Ertong Li

Author Affiliations +

Proceedings Volume 13539, Sixteenth International Conference on Graphics and Image Processing (ICGIP 2024); 1353908 (2025) https://doi.org/10.1117/12.3057934
Event: Sixteenth International Conference on Graphics and Image Processing (ICGIP 2024), 2024, Nanjing, China

Abstract

Few-Shot object detection is a task that trains a model to effectively recognize and locate novel classes of objects given a very limited amount of labeled samples. However, due to the scarcity of samples for novel classes, the model always lacks sufficient feature discrimination between base classes and the few-shot novel classes, conventional classification methods are prone to confuse similar categories, affecting the accuracy of object detection. In this paper, the query calibration method via graph-centrality-based prototype (GC-PQC) and a Gradual Gradient Isolation (GGI) is proposed. The GC-PQC method constructs intra-class correlation models using graph centrality measures to enhance feature representation and alleviate inter-class confusion. Meanwhile, the GGI module progressively decouples the gradients of backpropagation to promote feature independence during the fine-tuning process. Together, these two methods improve the performance of few-shot object detection models and enhance the feature representation ability of novel classes. Experiment show that our framework achieves a 2%-5% increase in accuracy on novel classes across multiple datasets, demonstrating its effectiveness in addressing the challenges of few-shot object detection.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zhoufeng Liu, Xinnan Shao, and Ertong Li "Few-shot object detection via query feature calibration", Proc. SPIE 13539, Sixteenth International Conference on Graphics and Image Processing (ICGIP 2024), 1353908 (13 February 2025); https://doi.org/10.1117/12.3057934

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