Dual-Attention Sparse R-CNN via Single ROI Transformer and Dynamic CBAM
- Authors
- Park, S.; Lee, S.; Kang, J.; Park, S.; Choi, S.; Paik, Joonki
- Issue Date
- Oct-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- CBAM; dual attention; object detection; R-CNN; transformer
- Citation
- 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
- Journal Title
- 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59960
- DOI
- 10.1109/ICCE-Asia57006.2022.9954801
- ISSN
- 0000-0000
- Abstract
- A critical drawback of CNN-based object detection is an additional post processing such as non-maximum suppression(NMS). Recent works have solved that problem by applying a vision transformer, which is able to make sparse correlation between feature maps and proposal embedding. Sparse R-CNN, which is end-to-end object detection network, applies dynamic convolution for the correlation but requires many parameters. Based on the sparse R-CNN, this paper presents a dual-attention module for accurate and efficient end-to-end object detection. The proposed dual-attention method consists of: i) dynamic CBAM, which is more efficient than dynamic convolution and ii) single ROI transformer. Experimental results show that the proposed method not only is efficient in the sense of reduced number of parameters but also improves the performance. © 2022 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59960)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.