Self-supervised object tracking with cycle-consistent siamese networks

Weihao Yuan, Michael Yu Wang, Qifeng Chen

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther


Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training. In this work, we exploit an end-to-end Siamese network in a cycle-consistent self-supervised framework for object tracking. Self-supervision can be performed by taking advantage of the cycle consistency in the forward and backward tracking. To better leverage the end-to-end learning of deep networks, we propose to integrate a Siamese region proposal and mask regression network in our tracking framework so that a fast and more accurate tracker can be learned without the annotation of each frame. The experiments on the VOT dataset for visual object tracking and on the DAVIS dataset for video object segmentation propagation show that our method outperforms prior approaches on both tasks.

Original languageEnglish
Title of host publication2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781728162126
Publication statusPublished - 24 Oct 2020
Externally publishedYes
EventIEEE/RSJ International Conference on Intelligent Robots and Systems 2020 - Virtual, Las Vegas, United States of America
Duration: 24 Jan 202124 Jan 2021 (Website)

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866


ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems 2020
Abbreviated titleIROS 2020
Country/TerritoryUnited States of America
CityLas Vegas
Internet address

Cite this