Dong Chen

Dong Chen


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
17 August 2019 in Lecture Notes in Electrical Engineering
Verified
Book Chapter
Closed access
PDF file
SFShidong Fang
Shidong Fang
DCDong Chen
Dong Chen
QNQuanli Ning
Quanli Ning
LMLiang Ma
Liang Ma
JLJunjian Li
Junjian Li

10 October 2024 in IEEE Access
Verified
Journal Article
Open access
ZSZiwen Sun
Ziwen Sun
ZXZhizhong Xi
Zhizhong Xi
HLHao Li
Hao Li
CLChong Ling
Chong Ling
DCDong Chen
Dong Chen
XQXiaoyan Qin
Xiaoyan Qin
Overcoming the high cost of self-attention operation in Transformer-based object detection methods and improving the detection accuracy of small objects is one of the difficulties in the field of object detection research. This paper designs a progressive assisted object detection method PaoDet based on Transformer, which uses common feature extraction backbone such as Resnet and ViT to extract multi-scale features of the input image, and uses RPN(Region Proposal Network) to extract proposals of different scales; Subsequently, a progressive modeling approach was adopted to perform self-attention and cross-attention operations on proposals of different scales from large to small, achieving feature interaction between instances, ensuring high detection efficiency and low computational complexity. During the training process, each layer of the network has certain generalization ability for detecting adjacent scale objects under the supervision of a dynamic scale division method. Compared with state-of-the-art object detection methods on COCO and UAVDT datasets, the effectiveness and superiority of the proposed method were demonstrated.