Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking

TL;DR

This paper introduces HiT and DyHiT, efficient hierarchical transformer-based visual trackers that achieve high speed and accuracy on resource-limited devices through innovative modules and dynamic routing strategies.

Contribution

The paper presents a novel lightweight hierarchical ViT framework with a bridge module and dual-image encoding, along with a dynamic routing approach for adaptive tracking efficiency.

Findings

HiT achieves 61 fps on NVIDIA Jetson AGX with 64.6% AUC on LaSOT.

DyHiT adapts to scene complexity, reaching 111 fps with 62.4% AUC.

The training-free acceleration boosts existing trackers' speed by 2.68 times.

Abstract

Transformer-based visual trackers have demonstrated significant advancements due to their powerful modeling capabilities. However, their practicality is limited on resource-constrained devices because of their slow processing speeds. To address this challenge, we present HiT, a novel family of efficient tracking models that achieve high performance while maintaining fast operation across various devices. The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality. Additionally, we introduce a dual-image position encoding approach to effectively encode spatial information. HiT achieves an impressive speed of 61 frames per second (fps) on the NVIDIA Jetson AGX platform, alongside a competitive AUC of 64.6% on the LaSOT benchmark, outperforming all previous efficient trackers.Building on HiT, we propose DyHiT, an efficient dynamic tracker that flexibly adapts to scene complexity by selecting routes with varying computational requirements. DyHiT uses search area features extracted by the backbone network and inputs them into an efficient dynamic router to classify tracking scenarios. Based on the classification, DyHiT applies a divide-and-conquer strategy, selecting appropriate routes to achieve a superior trade-off between accuracy and speed. The fastest version of DyHiT achieves 111 fps on NVIDIA Jetson AGX while maintaining an AUC of 62.4% on LaSOT.Furthermore, we introduce a training-free acceleration method based on the dynamic routing architecture of DyHiT. This method significantly improves the execution speed of various high-performance trackers without sacrificing accuracy. For instance, our acceleration method enables the state-of-the-art tracker SeqTrack-B256 to achieve a 2.68 times speedup on an NVIDIA GeForce RTX 2080 Ti GPU while maintaining the same AUC of 69.9% on the LaSOT.