Yangyang Liu
Research Subjects
Yangyang Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Dianxi Shi
College of Computer Science and Technology, National University of Defense Technology, Changsha, China; Intelligent Game and Decision Lab (IGDL), Beijing, China
2 shared publications Shaowu Yang
National University of Defense Technology
1 shared publication- Xiaodong Yi
National University of Defense Technology
1 shared publication Yanyan Shi
National University of Defense Technology
1 shared publication- Yanyan Shi
College of Computer, National University of Defense Technology, Changsha, 410073, China
1 shared publication Yi Zhang
Defense Innovation Institute
1 shared publication
Latest Publications
- Open Access
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-21
UEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection
Object detection models based on feature pyramid networks have made significant progress in general object detection. However, small object detection is still a challenge for the existing models. In this paper, we think that two factors in the existing feature pyramid networks inhibit the performance of small object detection. The first one is that the different feature domains of shallow and deep layer features inhibit the model performance. The second one is that the accumulation of upper layer features leads to feature aliasing effect on the lower layer features, which interferes with the representations of small object features. Therefore, we propose Unified and Enhanced Feature Pyramid Networks (UEFPN) to improve the APs and ARs of small object detection. It has the following three characteristics: (1) Using the deep features of high-resolution image and original image to form the multi-scale features of unified domain. (2) In multi-scale features fusion, we learn the importance of upper layer features with the Channel Attention Fusion module (CAF) , to optimize feature aliasing effect and enhance the context information of shallow layer features. (3) UEFPN can be quickly applied to different models. The results of many experiments show that the models with UEFPN achieve significant performance improvement in small object detection compared with the baseline models.
- 17 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (2s) , 1-21
Open AccessUEFPN: Unified and Enhanced Feature Pyramid Networks for Small Object Detection
Object detection models based on feature pyramid networks have made significant progress in general object detection. However, small object detection is still a challenge for the existing models. In this paper, we think that two factors in the existing feature pyramid networks inhibit the performance of small object detection. The first one is that the different feature domains of shallow and deep layer features inhibit the model performance. The second one is that the accumulation of upper layer features leads to feature aliasing effect on the lower layer features, which interferes with the representations of small object features. Therefore, we propose Unified and Enhanced Feature Pyramid Networks (UEFPN) to improve the APs and ARs of small object detection. It has the following three characteristics: (1) Using the deep features of high-resolution image and original image to form the multi-scale features of unified domain. (2) In multi-scale features fusion, we learn the importance of upper layer features with the Channel Attention Fusion module (CAF) , to optimize feature aliasing effect and enhance the context information of shallow layer features. (3) UEFPN can be quickly applied to different models. The results of many experiments show that the models with UEFPN achieve significant performance improvement in small object detection compared with the baseline models.
- 4 November 2022
- Published by Springer Nature
- p. 504-515
Efficient Scale Divide and Conquer Network for Object Detection
- 4 November 2022
- Published by Springer Nature
- p. 504-515
Efficient Scale Divide and Conquer Network for Object Detection