TY - GEN
T1 - A Double Stream Module in Backbone for Object Detection Network
AU - He, Xuanfang
AU - Ding, Yan
AU - Yuan, Yating
AU - Liang, Weidong
AU - Huang, Xinliang
AU - Shan, Jiayuan
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/5/28
Y1 - 2021/5/28
N2 - The representation ability of the network is crucial for object detection. In this paper, we present a novel building block named double stream block to construct a backbone called double stream module (DSM) to improve the representation ability of object detection networks. The double stream block is designed by fusing the shuffle branch and the non shuffle branch with a weight layer. To make our block adaptive for the depth of the convolutional layer, a shortcut connection is adopted after the double stream fusion. After that, DSM is built as a backbone and integrated into Faster-RCNN, Cascade-RCNN, DetectoRS detection system to verify its applicability. On the VisDrone dataset of VAV, the evaluation results for object detection show that the double stream design can significantly increase the representation ability of the network, and our approach gains 2.0, 0.5and 1.1 mAP improvements in the detection systems mentioned above respectively.
AB - The representation ability of the network is crucial for object detection. In this paper, we present a novel building block named double stream block to construct a backbone called double stream module (DSM) to improve the representation ability of object detection networks. The double stream block is designed by fusing the shuffle branch and the non shuffle branch with a weight layer. To make our block adaptive for the depth of the convolutional layer, a shortcut connection is adopted after the double stream fusion. After that, DSM is built as a backbone and integrated into Faster-RCNN, Cascade-RCNN, DetectoRS detection system to verify its applicability. On the VisDrone dataset of VAV, the evaluation results for object detection show that the double stream design can significantly increase the representation ability of the network, and our approach gains 2.0, 0.5and 1.1 mAP improvements in the detection systems mentioned above respectively.
KW - double stream module
KW - object detection
UR - http://www.scopus.com/inward/record.url?scp=85113741285&partnerID=8YFLogxK
U2 - 10.1109/ICAIBD51990.2021.9458965
DO - 10.1109/ICAIBD51990.2021.9458965
M3 - Conference contribution
AN - SCOPUS:85113741285
T3 - 2021 4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021
SP - 567
EP - 571
BT - 2021 4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021
Y2 - 28 May 2021 through 31 May 2021
ER -