DP-YOLO: Effective Improvement Based on YOLO Detector
-
Published:2023-10-25
Issue:21
Volume:13
Page:11676
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Wang Chao1, Wang Qijin23ORCID, Qian Yu1, Hu Yating1, Xue Ying1, Wang Hongqiang3
Affiliation:
1. School of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230601, China 2. School of Big Data and Artificial Intelligence, Anhui Xinhua University, Hefei 230088, China 3. Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
Abstract
YOLOv5 remains one of the most widely used real-time detection models due to its commendable performance in accuracy and generalization. However, compared to more recent detectors, it falls short in label assignment and leaves significant room for optimization. Particularly, recognizing targets with varying shapes and poses proves challenging, and training the detector to grasp such features requires expert verification or collective discussion during the dataset labeling process, especially in domain-specific contexts. While deformable convolutions offer a partial solution, their extensive usage can enhance detection capabilities but at the expense of increased computational effort. We introduce DP-YOLO, an enhanced target detector that efficiently integrates the YOLOv5s backbone network with deformable convolutions. Our approach optimizes the positive sample selection during label assignment, resulting in a more scientifically grounded process. Notably, experiments on the COCO benchmark validate the efficacy of DP-YOLO, which utilizes an image size of [640, 640], achieves a remarkable 41.2 AP, and runs at an impressive 69 fps on an RTX 3090. Comparatively, DP-YOLO outperforms YOLOv5s by 3.2 AP, with only a small increase in parameters and GFLOPSs. These results demonstrate the significant advancements made by our proposed method.
Funder
national natural science foundation of China Anhui province’s quality engineering project Academic funding project for top talents of disciplines in Colleges and universities of Anhui Province
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference38 articles.
1. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA. 2. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile. 3. Faster r-cnn: Towards real-time object detection with region proposal networks;Ren;Adv. Neural Inf. Process. Syst.,2015 4. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA. 5. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I 14.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|