Metraipolis › archive › dc_4eda547f331c

LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking — arXiv:2609.33306

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33306
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:30.455Z
SHA-256 of the archived text
b4a7d6db120b97505c9197d21166288838bd4c624969bca39d068013917c13a1
Stable URL of this page
https://metraipolis.com/documento/dc_4eda547f331c

How to cite

LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking — arXiv:2609.33306 — arXiv (en), https://arxiv.org/abs/2609.33306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4eda547f331c (Metraipolis archive dc_4eda547f331c, sha256 b4a7d6db120b97505c9197d21166288838bd4c624969bca39d068013917c13a1)
BibTeX
@misc{dc4eda547f331c,
  title = {LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking — arXiv:2609.33306},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33306},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4eda547f331c; sha256 b4a7d6db120b97505c9197d21166288838bd4c624969bca39d068013917c13a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current Transformer-based tracking methods typically stack multiple Transformer blocks with separate parameters to model interactions between the target template and the search region for target localization. These trackers often incur substantial parameter overhead from stacked blocks, making their deployment on resource-limited devices difficult. To address this, we propose a parameter-efficient Transformer tracking framework, dubbed LoopTrack, which repeatedly applies a set of Transformer blocks with shared parameters to interact features in a looped architecture for tracking, significantly reducing the number of parameters. To further exploit target cues, we present two lightweight designs, including target-aware looping (TAL) and gated target memory (GTM). The former applies intermediate target information generated by one loop to guide feature interaction in the subsequent loop, enabling progressive feature refinement, while the latter maintains a compact memory across frames, which is incorporated into the loop process to provide long-term information to the tracker, mitigating temporal drift in tracking. Compared to existing Transformer trackers, LoopTrack enables multiple rounds of feature interaction with fewer model parameters, making it resource-friendly for deployment. In extensive experiments on multiple datasets, LoopTrack shows a favorable accuracy-parameter trade-off. In particular, our LoopTrack$_{\rm One}$, with a single shared Transformer block, achieves 66.2\% SUC score on LaSOT with only 3.4M parameters, while LoopTrack$_{\rm Three}$, using three shared blocks, achieves 69.3\% SUC score with 6.4M parameters, surpassing existing parameter-efficient tracking methods with comparable or larger model size. With LoopTrack, we aim to establish a simple yet strong baseline for parameter-efficient Transformer tracking. Our code and models will be released.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33306 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T23:29:27.180Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).