S2SiamFC: Self-supervised Fully Convolutional Siamese Network for Visual Tracking

Chon Hou Sio, Yu Jen Ma, Hong Han Shuai, Jun Cheng Chen, Wen Huang Cheng

研究成果: Conference contribution同行評審

26 引文 斯高帕斯(Scopus)

摘要

To exploit rich information from unlabeled data, in this work, we propose a novel self-supervised framework for visual tracking which can easily adapt the state-of-the-art supervised Siamese-based trackers into unsupervised ones by utilizing the fact that an image and any cropped region of it can form a natural pair for self-training. Besides common geometric transformation-based data augmentation and hard negative mining, we also propose adversarial masking which helps the tracker to learn other context information by adaptively blacking out salient regions of the target. The proposed approach can be trained offline using images only without any requirement of manual annotations and temporal information from multiple consecutive frames. Thus, it can be used with any kind of unlabeled data, including images and video frames. For evaluation, we take SiamFC as the base tracker and name the proposed self-supervised method as S2SiamFC. Extensive experiments and ablation studies on the challenging VOT2016 and VOT2018 datasets are provided to demonstrate the effectiveness of the proposed method which not only achieves comparable performance to its supervised counterpart and other unsupervised methods requiring multiple frames.

原文English
主出版物標題MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
發行者Association for Computing Machinery, Inc
頁面1948-1957
頁數10
ISBN(電子)9781450379885
DOIs
出版狀態Published - 12 10月 2020
事件28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States
持續時間: 12 10月 202016 10月 2020

出版系列

名字MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia

Conference

Conference28th ACM International Conference on Multimedia, MM 2020
國家/地區United States
城市Virtual, Online
期間12/10/2016/10/20

指紋

深入研究「S2SiamFC: Self-supervised Fully Convolutional Siamese Network for Visual Tracking」主題。共同形成了獨特的指紋。

引用此