Progressive Scaling Visual Object Tracking

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hong, Jack, Yan, Shilin, Xiao, Zehao, Cai, Jiayin, Jiang, Xiaolong, Hu, Yao, Ding, Henghui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918037114847232
author Hong, Jack
Yan, Shilin
Xiao, Zehao
Cai, Jiayin
Jiang, Xiaolong
Hu, Yao
Ding, Henghui
author_facet Hong, Jack
Yan, Shilin
Xiao, Zehao
Cai, Jiayin
Jiang, Xiaolong
Hu, Yao
Ding, Henghui
contents In this work, we propose a progressive scaling training strategy for visual object tracking, systematically analyzing the influence of training data volume, model size, and input resolution on tracking performance. Our empirical study reveals that while scaling each factor leads to significant improvements in tracking accuracy, naive training suffers from suboptimal optimization and limited iterative refinement. To address this issue, we introduce DT-Training, a progressive scaling framework that integrates small teacher transfer and dual-branch alignment to maximize model potential. The resulting scaled tracker consistently outperforms state-of-the-art methods across multiple benchmarks, demonstrating strong generalization and transferability of the proposed method. Furthermore, we validate the broader applicability of our approach to additional tasks, underscoring its versatility beyond tracking.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Progressive Scaling Visual Object Tracking
Hong, Jack
Yan, Shilin
Xiao, Zehao
Cai, Jiayin
Jiang, Xiaolong
Hu, Yao
Ding, Henghui
Computer Vision and Pattern Recognition
In this work, we propose a progressive scaling training strategy for visual object tracking, systematically analyzing the influence of training data volume, model size, and input resolution on tracking performance. Our empirical study reveals that while scaling each factor leads to significant improvements in tracking accuracy, naive training suffers from suboptimal optimization and limited iterative refinement. To address this issue, we introduce DT-Training, a progressive scaling framework that integrates small teacher transfer and dual-branch alignment to maximize model potential. The resulting scaled tracker consistently outperforms state-of-the-art methods across multiple benchmarks, demonstrating strong generalization and transferability of the proposed method. Furthermore, we validate the broader applicability of our approach to additional tasks, underscoring its versatility beyond tracking.
title Progressive Scaling Visual Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19990