Optimized object detection with score attention and spatially modulated co-attention

Zhenjun Wu; Zhong Qu; Shuheng Zhao

doi:10.1117/12.3033638

13 June 2024 Optimized object detection with score attention and spatially modulated co-attention

Zhenjun Wu, Zhong Qu, Shuheng Zhao

Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 131805U (2024) https://doi.org/10.1117/12.3033638
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China

Abstract

Detection Transformer (DETR) is a novel end-to-end object detection paradigm based on the Transformer structure proposed in recent years. It eliminates the need for manual components like Non-Maximum Suppression (NMS) to achieve comparable accuracy to traditional detection methods. Despite its innovative approach, there are still limitations, particularly in terms of low detection accuracy for small objects and long convergence time of the model, which hinder its effectiveness across various detection scenarios. In this paper, we propose an enhanced DETR encoder and introduce a spatially modulated co-attention module during the decoder phase to address these issues. The enhanced encoder utilizes a new score attention mechanism characterized by low computational complexity and enhances the detection accuracy of small objects through multi-scale feature fusion. Additionally, we introduce a spatially modulated coattention module to maintain query stability during the decoder stage by incorporating spatial priors. Experimental results demonstrate that our proposed algorithm exhibits excellent performance with an achieved mAP@0.5 of 45.2% on the MSCOCO 2017 dataset.

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

Citation Download Citation

Zhenjun Wu, Zhong Qu, and Shuheng Zhao "Optimized object detection with score attention and spatially modulated co-attention", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 131805U (13 June 2024); https://doi.org/10.1117/12.3033638

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Object detection

Data modeling

Modulation

Education and training

Performance modeling

Transformers

Deformation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years