Progressive Scaling Visual Object Tracking

TL;DR

This paper introduces a progressive scaling training strategy for visual object tracking, utilizing a novel DT-Training framework with teacher transfer and dual-branch alignment to improve accuracy and generalization.

Contribution

The paper presents a new progressive scaling framework for tracking that effectively combines data, model size, and resolution, outperforming existing methods.

Findings

Scaled tracker outperforms state-of-the-art methods

Progressive scaling improves tracking accuracy

Method demonstrates strong generalization and transferability

Abstract

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.