UETrack：统一高效的单目标跟踪框架
UETrack: A Unified and Efficient Framework for Single Object Tracking
Token-Pooling-based Mixture-of-Experts 和 Target-aware Adaptive Distillation 可复用于多模态视觉任务的高效部署，在保持精度的同时显著降低计算开销。
原文依据 UETrack achieves a superior speed-accuracy trade-off compared to pervious methods.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着现实世界需求的增长，高效跟踪受到越来越多的关注。然而，大多数现有方法局限于RGB输入，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设计，使其过于沉重和缓慢，难以在资源受限的部署中使用。为解决这些限制，我们提出了UETrack，一个统一高效的单目标跟踪框架。UETrack展示了高度的实用性和多功能性，能够高效处理包括RGB、深度、热成像、事件和语言在内的多种模态，并填补了高效多模态跟踪的空白。它引入了两个关键组件：基于Token池化的混合专家机制，通过特征聚合和专家专业化增强建模能力；以及目标感知的自适应蒸馏策略，根据样本特性选择性执行蒸馏，减少冗余监督并提升性能。在3个硬件平台上的12个基准测试中进行的广泛实验表明，与先前方法相比，UETrack实现了更优的速度-精度权衡。例如，UETrack-B在LaSOT上达到69.2%的AUC，并在GPU/CPU/AGX上分别以163/56/60 FPS运行，展示了强大的实用性和多功能性。代码可在https://github.com/kangben258/UETrack获取。
英文原文摘要 1365 字符
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, a unified and 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 pervious 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 https://github.com/kangben258/UETrack.