Abstract
With growing real-world demands, efficient tracking has received increasing attention. However, most existing methods are limited to RGB inputs and struggle in multi-modal scenarios. Moreover, current multi-modal tracking approaches typically use complex designs, making them too heavy and slow for resource-constrained deployment. To tackle these limitations, we propose UETrack, an efficient framework for single object tracking. UETrack demonstrates high practicality and versatility, efficiently handling multiple modalities including RGB, Depth, Thermal, Event, and Language, and addresses the gap in efficient multi-modal tracking. It introduces two key components: a Token-Pooling-based Mixture-of-Experts mechanism that enhances modeling capacity through feature aggregation and expert specialization, and a Target-aware Adaptive Distillation strategy that selectively performs distillation based on sample characteristics, reducing redundant supervision and improving performance. Extensive experiments on 12 benchmarks across 3 hardware platforms show that UETrack achieves a superior speed-accuracy trade-off compared to previous methods. For instance, UETrack-B achieves 69.2% AUC on LaSOT and runs at 163/56/60 FPS on GPU/CPU/AGX, demonstrating strong practicality and versatility. Code is available at this https URL.
Abstract (translated)
随着现实世界需求的增长，高效的追踪技术受到了越来越多的关注。然而，大多数现有的方法仅限于RGB输入，并且在多模态场景中表现不佳。此外，当前的多模态跟踪方法通常采用复杂的架构设计，这使得它们过于庞大和缓慢，难以应用于资源受限的环境中。为了解决这些问题，我们提出了UETrack，这是一个用于单对象追踪的有效框架。UETrack展示了极高的实用性和灵活性，能够高效地处理包括RGB、深度、热感、事件及语言在内的多种模态，并解决了有效多模态跟踪领域的空白。 UETrack引入了两个关键组件：基于Token-Pooling的专家混合机制，通过特征聚合和专家专业化来增强建模能力；以及目标感知自适应蒸馏策略，根据样本特性进行选择性蒸馏以减少冗余监督并提高性能。在三个硬件平台上的12个基准测试中进行了广泛的实验表明，UETrack相较于先前的方法实现了更优的速度-精度权衡。例如，在LaSOT数据集上，UETrack-B达到了69.2%的AUC，并且分别在GPU、CPU和AGX平台上以每秒163帧、56帧和60帧的速度运行，展示了其强大的实用性和灵活性。代码可在提供的链接处获得。 该研究通过提供一个轻量级但高效的解决方案来应对现有技术的问题，这使得UETrack特别适合于资源受限的部署场景，并且在多模态追踪任务上表现出色。
URL
https://arxiv.org/abs/2603.01412
