ScaledDETR: An alight weight object detection model for autonomous driving
Mansoura Engineering Journal · 29.10.2024 · 49 (5)
DOI: 10.58491/2735-4202.3238 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mansoura Engineering Journal, online erschienen am 29.10.2024. Verfasst von Ali Elhenidy und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
End-to-end object detection is one of the recent trends in object detection; however, it is time- and memory-consuming due to the Transformer encoder-decoder (TED) module. Detection TRansformer (DETR) is the first end-to-end object detector using a TED architecture. Despite achieving competitive performance, it suffers from slow convergence due to a long sequence of attention and the whole image. In this paper, ScaledDETR is proposed to handle the slow convergence issue in DETR and speed up the training process by implementing end-to-end detection based on the latest efficient backbone with fewer parameters. ScaledDETR proposes an efficient model with fewer parameters by replacing the ResNet backbone with EfficientNet, which is an efficient CNN backbone. The recent Relative Position Encoding (RPE) is adopted rather than standard Position Encoding (PE) which proves to gain 1.3% (AP) improvement. ScaledDETR invokes a simple architecture that runs on a single GPU that could be suitable for autonomous driving applications. The proposed model is trained for 20 epochs, which are 25x fewer than the number of epochs in DETR, and achieves competitive results with state-of-the-art object detection methods. The proposed method achieved 41.7 Ap on the COCO dataset compared with Faster RCNN, which achieved 40.2 Ap.
Zitieren
APA
Elhenidy, A., Mohamed, L., Yassien, A., & saafan, M. (2024). ScaledDETR: An alight weight object detection model for autonomous driving. Mansoura Engineering Journal, 49(5). https://doi.org/10.58491/2735-4202.3238
Vancouver
Elhenidy A, Mohamed L, Yassien A, saafan M. ScaledDETR: An alight weight object detection model for autonomous driving. Mansoura Engineering Journal. 2024;49(5). doi:10.58491/2735-4202.3238
BibTeX
@article{Elhenidy2024,
author = {Elhenidy, Ali and Mohamed, Labib and Yassien, Amira and saafan, Mahmoud},
title = {ScaledDETR: An alight weight object detection model for autonomous driving},
journal = {Mansoura Engineering Journal},
year = {2024},
volume = {49},
number = {5},
doi = {10.58491/2735-4202.3238}
}
EUVIMED