TY - GEN
T1 - SGE NET
T2 - 2021 IEEE International Conference on Image Processing, ICIP 2021
AU - Su, Rui
AU - Huang, Wenjing
AU - Ma, Haoyu
AU - Song, Xiaowei
AU - Hu, Jinglu
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich temporal information. The RNN-based algorithm is an effective way to enhance detection performance in videos with temporal information. However, most studies in this area only focus on accuracy while ignoring the calculation cost and the number of parameters. In this paper, we propose an efficient method that combines channel-reduced convolutional GRU (Squeezed GRU), and Information Entropy map for video object detection (SGE-Net). The experimental results validate the accuracy improvement, computational savings of the Squeezed GRU, and superiority of the information entropy attention mechanism on the classification performance. The mAP has increased by 3.7 contrasted with the baseline, and the number of parameters has decreased from 6.33 million to 0.67 million compared with the standard GRU.
AB - Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich temporal information. The RNN-based algorithm is an effective way to enhance detection performance in videos with temporal information. However, most studies in this area only focus on accuracy while ignoring the calculation cost and the number of parameters. In this paper, we propose an efficient method that combines channel-reduced convolutional GRU (Squeezed GRU), and Information Entropy map for video object detection (SGE-Net). The experimental results validate the accuracy improvement, computational savings of the Squeezed GRU, and superiority of the information entropy attention mechanism on the classification performance. The mAP has increased by 3.7 contrasted with the baseline, and the number of parameters has decreased from 6.33 million to 0.67 million compared with the standard GRU.
KW - Computational savings
KW - Information entropy attention
KW - Squeezed GRU
KW - Video object detection
UR - http://www.scopus.com/inward/record.url?scp=85120075226&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85120075226&partnerID=8YFLogxK
U2 - 10.1109/ICIP42928.2021.9506081
DO - 10.1109/ICIP42928.2021.9506081
M3 - Conference contribution
AN - SCOPUS:85120075226
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 689
EP - 693
BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PB - IEEE Computer Society
Y2 - 19 September 2021 through 22 September 2021
ER -