Domain-Specific On-Device Object Detection Method
Department of Electronics and Communications Engineering, Kwangwoon University, Seoul 01897, Korea
*
Author to whom correspondence should be addressed.
Academic Editors: Andrea Prati, Carlos A. Iglesias, Luis Javier García Villalba and Vincent A. Cicirello
Entropy 2022, 24(1), 77; https://doi.org/10.3390/e24010077
Received: 26 November 2021
/
Revised: 25 December 2021
/
Accepted: 29 December 2021
/
Published: 1 January 2022
(This article belongs to the Topic Machine and Deep Learning)
Object detection is a significant activity in computer vision, and various approaches have been proposed to detect varied objects using deep neural networks (DNNs). However, because DNNs are computation-intensive, it is difficult to apply them to resource-constrained devices. Here, we propose an on-device object detection method using domain-specific models. In the proposed method, we define object of interest (OOI) groups that contain objects with a high frequency of appearance in specific domains. Compared with the existing DNN model, the layers of the domain-specific models are shallower and narrower, reducing the number of trainable parameters; thus, speeding up the object detection. To ensure a lightweight network design, we combine various network structures to obtain the best-performing lightweight detection model. The experimental results reveal that the size of the proposed lightweight model is 21.7 MB, which is 91.35% and 36.98% smaller than those of YOLOv3-SPP and Tiny-YOLO, respectively. The f-measure achieved on the MS COCO 2017 dataset were 18.3%, 11.9% and 20.3% higher than those of YOLOv3-SPP, Tiny-YOLO and YOLO-Nano, respectively. The results demonstrated that the lightweight model achieved higher efficiency and better performance on non-GPU devices, such as mobile devices and embedded boards, than conventional models.
View Full-Text
Keywords:
object detection; domain-specific; on-device; lightweight network
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Kang, S.; Hwang, J.; Chung, K. Domain-Specific On-Device Object Detection Method. Entropy 2022, 24, 77. https://doi.org/10.3390/e24010077
AMA Style
Kang S, Hwang J, Chung K. Domain-Specific On-Device Object Detection Method. Entropy. 2022; 24(1):77. https://doi.org/10.3390/e24010077
Chicago/Turabian StyleKang, Seongju, Jaegi Hwang, and Kwangsue Chung. 2022. "Domain-Specific On-Device Object Detection Method" Entropy 24, no. 1: 77. https://doi.org/10.3390/e24010077
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
