面向多目标跟踪的表示对齐对比正则化方法
Representation Alignment Contrastive Regularization for Multi-Object Tracking
AI总结：
针对多目标跟踪中时空关系建模的效果与可解释性平衡问题，提出基于表示对齐的对比正则化方法，结合轻量单层transformer，以极小开销提升现有跟踪网络性能。
摘要：
多目标跟踪算法的高性能实现高度依赖数据关联阶段对时空关系的建模。主流方法包括基于规则和基于深度学习的时空关系建模方法。前者依赖物理运动规律，适用范围更广，但在复杂目标运动场景下效果欠佳；后者虽能实现高性能，但缺乏可解释性且模块设计复杂。本研究旨在简化基于深度学习的时空关系模型，并为数据关联的特征引入可解释性。具体而言，采用轻量级单层transformer编码器建模时空关系。为提升特征的可解释性，基于时空一致性规则，提出两种基于表示对齐的对比正则化损失。通过对亲和度矩阵进行加权求和，对齐后的特征可无缝集成到原有跟踪流程的数据关联阶段。实验结果表明，该模型在不过度增加复杂度的前提下，提升了多数现有跟踪网络的性能，训练开销增幅极小，计算与存储成本几乎可忽略不计。
英文摘要：
Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for spatio-temporal relationship modeling. While the former relies on physical motion laws, offering wider applicability but yielding suboptimal results for complex object movements, the latter, though achieving high-performance, lacks interpretability and involves complex module designs. This work aims to simplify deep learning-based spatio-temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single-layer transformer encoder is utilized to model spatio-temporal relationships. To make features more interpretative, two contrastive regularization losses based on representation alignment are proposed, derived from spatio-temporal consistency rules. By applying weighted summation to affinity matrices, the aligned features can seamlessly integrate into the data association stage of the original tracking workflow. Experimental results showcase that our model enhances the majority of existing tracking networks' performance without excessive complexity, with minimal increase in training overhead and nearly negligible computational and storage costs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
