Representation Alignment Contrastive Regularization for Multi-Object Tracking
This work addresses the need for more interpretable and efficient multi-object tracking algorithms, though it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of simplifying deep learning-based spatio-temporal relationship models in multi-object tracking by using a lightweight transformer encoder and contrastive regularization losses to enhance interpretability and performance, achieving improvements in most existing tracking networks with minimal computational overhead.
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.