DLUT: Decoupled Learning-Based Unsupervised Tracker
Author:
Xu Zhengjun1, Huang Detian12ORCID, Huang Xiaoqian2, Song Jiaxun1, Liu Hang1
Affiliation:
1. School of Engineering, Huaqiao University, Quanzhou 362021, China 2. School of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
Abstract
Unsupervised learning has shown immense potential in object tracking, where accurate classification and regression are crucial for unsupervised trackers. However, the classification and regression branches of most unsupervised trackers calculate object similarities by sharing cross-correlation modules. This leads to high coupling between different branches, thus hindering the network performance. To address the above issue, we propose a Decoupled Learning-based Unsupervised Tracker (DLUT). Specifically, we separate the training pipelines of different branches to unlock their inherent learning potential so that different branches can fully explore the focused feature regions of interest. Furthermore, we design independent adaptive decoupling-correlation modules according to the characteristics of each branch to obtain more discriminative and easily locatable feature response maps. Finally, to suppress the noise interference brought by unsupervised pseudo-label training and highlight the foreground object, we propose a novel suppression-ranking-based unsupervised training strategy. Extensive experiments demonstrate that our DLUT outperforms state-of-the-art unsupervised trackers.
Funder
National Key R & D Program of China National Natural Science Foundation of China Fundamental Research Funds for the Central Universities
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference68 articles.
1. Visual object tracking: A survey;Chen;Comput. Vis. Image Underst.,2022 2. Wang, N., Song, Y., Ma, C., Zhou, W., Liu, W., and Li, H. (2019, January 16–20). Unsupervised Deep Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. 3. Zheng, J., Ma, C., Peng, H., and Yang, X. (2021, January 11–17). Learning To Track Objects From Unlabeled Videos. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada. 4. Shen, Q., Qiao, L., Guo, J., Li, P., Li, X., Li, B., Feng, W., Gan, W., Wu, W., and Ouyang, W. (2022, January 19–24). Unsupervised Learning of Accurate Siamese Tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Orleans, LA, USA. 5. Jiang, B., Luo, R., Mao, J., Xiao, T., and Jiang, Y. (2018, January 8–14). Acquisition of Localization Confidence for Accurate Object Detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.
|
|