# Self-supervised Object Tracking with Cycle-consistent Siamese Networks

arXiv: https://arxiv.org/abs/2008.00637 · HTML: https://mlsanity.com/paper/2008.00637/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 11 of 11)

- [Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking](https://mlsanity.com/paper/2507.21606/) (2025)
- [An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2303.12535/) (2023)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images](https://mlsanity.com/paper/2404.16571/) (2024)
- [A topological solution to object segmentation and tracking](https://mlsanity.com/paper/2107.02036/) (2021)
- [MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency](https://mlsanity.com/paper/2303.09219/) (2023)
- [Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning](https://mlsanity.com/paper/2605.06092/) (2026)
- [Self-Supervised RGB-T Tracking with Cross-Input Consistency](https://mlsanity.com/paper/2301.11274/) (2023)
- [BackTrack: Robust template update via Backward Tracking of candidate template](https://mlsanity.com/paper/2308.10604/) (2023)
- [Learning Tracking Representations from Single Point Annotations](https://mlsanity.com/paper/2404.09504/) (2024)
- [End-to-End Self-Supervised RGB-T Tracking without Modality Misleading](https://mlsanity.com/paper/2609.37162/) (2026)

## Abstract (arXiv)

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.