Papers › Self-supervised Object Tracking with Cycle-consistent Siamese Networks

Self-supervised Object Tracking with Cycle-consistent Siamese Networks

3 Aug 2020arXiv:2008.00637archive 2025-07-28

Weihao Yuan, Michael Yu Wang, Qifeng Chen

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

weihaosky/CycleSiam officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject TrackingRegion ProposalSelf-Supervised LearningSemantic SegmentationVideo Object SegmentationVideo Semantic SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Siamese Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections