Wei Cheng

Wei Cheng

Auto-generated profile, based on publicly available information

Wei Cheng

School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 May 2023 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
XLXingzhu Liang
Xingzhu Liang
WCWei Cheng
Wei Cheng
Chunjiong ZhangChunjiong Zhang
Chunjiong Zhang
LWLixin Wang
Lixin Wang
XYXinyun Yan
Xinyun Yan
QCQing Chen
Qing Chen
Object detection includes three subtasks of predicting target position, classification, and confidence. In the mainstream object detection model, the model pursues internal structure refinement, and each subtask shares almost the same structure, which is a task-coupled structure. The task-coupled structure of the model reduces the training parameters, but it cannot be tuned on the network structure for each task separately, which can limit the model performance. We designed a task decoupled object detection network (YOLOD) based on YOLOv5, where YOLOD is decoupled immediately after the backbone network. By observing the loss convergence of each subtask, three network structures are designed separately and the branch size is controlled so that the model has fewer training parameters. At the same time, some experimental adjustments were made to YOLOD to accelerate the convergence speeds of the model. In addition, we add image contour information to the original three-channel image to assist model training and improve detection accuracy. The experiments demonstrate that the modified model is smaller in size and has the largest accuracy improvement on the small-scale model. without introducing any attention-based modules, YOLOD-S achieves a mAP improvement of 1.1% on the MS COCO dataset and 2.29% on the VOC dataset, and the larger model YOLOD-L achieves an accuracy of 48.8% on the COCO dataset.

1 August 2017 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
ZWZhenyu Wang
Zhenyu Wang
YWYanyun Wang
Yanyun Wang
WCWei Cheng
Wei Cheng
TCTao Chen
Tao Chen
HZHui Zhou
Hui Zhou