TY - GEN
T1 - An Improved Siamese Tracking Network Based On Self-Attention And Cross-Attention
AU - Lai, Yijun
AU - Song, Jianmei
AU - She, Haoping
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Deep Siamese visual tracking network SiamRPN++ is found that its success rate and robustness is unsatisfactory when meeting complex scenes such as occlusion, large deformation, interference of similar objects and long-time tracking. Refer to these, we propose an improvement strategy based on self-attention and cross-attention mechanism. For backbone, we use Channel and Space self-attention modules, and we using different cross channel attention modules between template features and search features in every three RPN modules, finally using special self-attention on similarity feature maps. These tricks effectively suppress interference, improve the features' quality and make progress in robustness. Comparing with original SiamRPN++ with parameters from official open-source frame, PySOT, our network improves robustness of 3% on VOT2018, accuracy of 2% and success rate of 3% on OTB100.
AB - Deep Siamese visual tracking network SiamRPN++ is found that its success rate and robustness is unsatisfactory when meeting complex scenes such as occlusion, large deformation, interference of similar objects and long-time tracking. Refer to these, we propose an improvement strategy based on self-attention and cross-attention mechanism. For backbone, we use Channel and Space self-attention modules, and we using different cross channel attention modules between template features and search features in every three RPN modules, finally using special self-attention on similarity feature maps. These tricks effectively suppress interference, improve the features' quality and make progress in robustness. Comparing with original SiamRPN++ with parameters from official open-source frame, PySOT, our network improves robustness of 3% on VOT2018, accuracy of 2% and success rate of 3% on OTB100.
KW - Siamese network
KW - cross-attention
KW - object tracking
KW - self-attention
UR - http://www.scopus.com/inward/record.url?scp=85181830297&partnerID=8YFLogxK
U2 - 10.1109/CCDC58219.2023.10326870
DO - 10.1109/CCDC58219.2023.10326870
M3 - Conference contribution
AN - SCOPUS:85181830297
T3 - Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023
SP - 466
EP - 470
BT - Proceedings of the 35th Chinese Control and Decision Conference, CCDC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 35th Chinese Control and Decision Conference, CCDC 2023
Y2 - 20 May 2023 through 22 May 2023
ER -