English

Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking

Computer Vision and Pattern Recognition 2025-07-30 v1

Abstract

The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework named \textbf{{\tracker}}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association. This allows for the simulation of appearance and motion variations of instances in real-world scenarios. Furthermore, an instance contrastive loss is designed to learn instance-level correspondences from a multi-view perspective, offering robust instance supervision without additional labels. This new design paradigm enables {\tracker} to effectively learn generic tracking representations in a self-supervised manner, while reducing reliance on extensive box annotations. Extensive experiments on nine benchmark datasets demonstrate that {\tracker} surpasses \textit{SOTA} self-supervised tracking methods, achieving an improvement of more than 25.3\%, 20.4\%, and 14.8\% in AUC (AO) score on the GOT10K, LaSOT, TrackingNet datasets, respectively. Code: https://github.com/GXNU-ZhongLab/SSTrack.

Keywords

Cite

@article{arxiv.2507.21606,
  title  = {Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking},
  author = {Yaozong Zheng and Bineng Zhong and Qihua Liang and Ning Li and Shuxiang Song},
  journal= {arXiv preprint arXiv:2507.21606},
  year   = {2025}
}

Comments

Accepted by AAAI2025

R2 v1 2026-07-01T04:23:37.701Z