Abstract
We present UniTrack, a plug-and-play graph-theoretic loss function designed to significantly enhance multi-object tracking (MOT) performance by directly optimizing tracking-specific objectives through unified differentiable learning. Unlike prior graph-based MOT methods that redesign tracking architectures, UniTrack provides a universal training objective that integrates detection accuracy, identity preservation, and spatiotemporal consistency into a single end-to-end trainable loss function, enabling seamless integration with existing MOT systems without architectural modifications. Through differentiable graph representation learning, UniTrack enables networks to learn holistic representations of motion continuity and identity relationships across frames. We validate UniTrack across diverse tracking models and multiple challenging benchmarks, demonstrating consistent improvements across all tested architectures and datasets including Trackformer, MOTR, FairMOT, ByteTrack, GTR, and MOTE. Extensive evaluations show up to 53\% reduction in identity switches and 12\% IDF1 improvements across challenging benchmarks, with GTR achieving peak performance gains of 9.7\% MOTA on SportsMOT.
Abstract (translated)
我们介绍 UniTrack，这是一种即插即用的图论损失函数，旨在通过统一可微学习直接优化特定于跟踪的目标来显著提升多目标跟踪（MOT）性能。与以往需要重新设计跟踪架构的基于图形的方法不同，UniTrack 提供了一个通用的训练目标，将检测精度、身份保持和时空一致性整合为一个单一的端到端可训练损失函数，从而无需对现有 MOT 系统进行架构修改即可实现无缝集成。 通过可微图表示学习，UniTrack 使网络能够跨帧学习运动连续性和身份关系的整体表示。我们在各种跟踪模型和多个具有挑战性的基准测试中验证了 UniTrack 的性能，展示了所有测试的架构和数据集（包括 Trackformer、MOTR、FairMOT、ByteTrack、GTR 和 MOTE）上的一致改进。 广泛的评估结果显示，在具有挑战性的基准测试中身份切换减少了高达 53%，IDF1 改进达 12%。在 SportsMOT 基准测试中，GTR 达到了峰值性能提升，即 MOTA（多目标跟踪精度）提高了 9.7%。
URL
https://arxiv.org/abs/2602.05037
