HT-DETR: accelerating convergence for detection transformer with hybrid task allocation

Shuheng Zhao; Zhong Qu; Zhenjun Wu

doi:10.1117/12.3041273

11 September 2024 HT-DETR: accelerating convergence for detection transformer with hybrid task allocation

Shuheng Zhao, Zhong Qu, Zhenjun Wu

Proceedings Volume 13253, Fourth International Conference on Signal Image Processing and Communication (ICSIPC 2024); 132531C (2024) https://doi.org/10.1117/12.3041273
Event: 4th International Conference on Signal Image Processing and Communication, 2024, Xi'an, China

Abstract

The DETR(Detection Transformer), based on the Transformer architecture, has shown great potential as an end-to-end object detection application in this field. It is worth noting that the DETR model uses the Hungarian algorithm for object prediction. However, due to the instability of the Hungarian matching algorithm itself, the model faces inconsistency issues in target optimization during early training stages, resulting in slower convergence speed. To address this challenge, this paper proposes an innovative hybrid task assignment algorithm. This algorithm increases the number of positive sample queries using one-to-many matching, allowing queries to predict multiple aspects of a single target and improving matching stability. Additionally, targets are grouped based on their true box sizes and corresponding grouping is applied to queries as well. Each query group is responsible for matching targets of specific sizes, significantly enhancing matching stability and accelerating model convergence process. Experimental results on COCO dataset demonstrate the effectiveness of this approach, showing outstanding performance in a single-scale DETR model with ResNet-50 backbone network achieving an average precision (AP) of 38.8% within 12 training epochs. Compared to baseline models with similar settings, it achieves a 3.2% AP improvement.

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

Citation Download Citation

Shuheng Zhao, Zhong Qu, and Zhenjun Wu "HT-DETR: accelerating convergence for detection transformer with hybrid task allocation", Proc. SPIE 13253, Fourth International Conference on Signal Image Processing and Communication (ICSIPC 2024), 132531C (11 September 2024); https://doi.org/10.1117/12.3041273

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

Education and training

Detection and tracking algorithms

Transformers

Data modeling

Performance modeling

Ablation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years