Few-shot object detection with anti-confusion grouping

Liang Peng; Fei Hu; Long Ye

doi:10.1117/12.2622618

4 March 2022 Few-shot object detection with anti-confusion grouping

Liang Peng, Fei Hu, Long Ye

Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021); 120840F (2022) https://doi.org/10.1117/12.2622618
Event: Fourteenth International Conference on Machine Vision (ICMV 2021), 2021, Rome, Italy

Abstract

Recent approaches have achieved excellent results on few-shot object detection. However, most detectors are easily confused by visually similar classes, leading to misclassification of interesting objects. In this work, we introduce an anti-confusion grouping mechanism for this problem. Our model can refine the results of the major multi-class classifier of the few-shot object detector with an anti-confusion module. Instead of maximizing the feature distribution distance of similar classes in the feature space, our approach uses additional auxiliary grouping module to distinguish similar classes on the same feature space as in base training phase. Concretely, the class groups are obtained according to the class visual similarity, and then they are utilized to train the auxiliary module. The main classifier, regressor and auxiliary anti-confusion module are end-to-end trained based on a multi-task loss. In the test phase, the auxiliary module is combined with the main classifier to provide the final classification result. Through extensive experiments, we demonstrate that our model outperforms well-established baselines for few-shot object detection. We also present analysis on various aspects of our model, aiming to provide some inspiration for future few-shot detection works.

Citation Download Citation

Liang Peng, Fei Hu, and Long Ye "Few-shot object detection with anti-confusion grouping", Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 120840F (4 March 2022); https://doi.org/10.1117/12.2622618

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