TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917976550146048 |
|---|---|
| author | Ding, Shuxiao Yang, Yutong Wiederer, Julian Braun, Markus Li, Peizheng Gall, Juergen Yang, Bin |
| author_facet | Ding, Shuxiao Yang, Yutong Wiederer, Julian Braun, Markus Li, Peizheng Gall, Juergen Yang, Bin |
| contents | Query denoising has become a standard training strategy for DETR-based detectors by addressing the slow convergence issue. Besides that, query denoising can be used to increase the diversity of training samples for modeling complex scenarios which is critical for Multi-Object Tracking (MOT), showing its potential in MOT application. Existing approaches integrate query denoising within the tracking-by-attention paradigm. However, as the denoising process only happens within the single frame, it cannot benefit the tracker to learn temporal-related information. In addition, the attention mask in query denoising prevents information exchange between denoising and object queries, limiting its potential in improving association using self-attention. To address these issues, we propose TQD-Track, which introduces Temporal Query Denoising (TQD) tailored for MOT, enabling denoising queries to carry temporal information and instance-specific feature representation. We introduce diverse noise types onto denoising queries that simulate real-world challenges in MOT. We analyze our proposed TQD for different tracking paradigms, and find out the paradigm with explicit learned data association module, e.g. tracking-by-detection or alternating detection and association, benefit from TQD by a larger margin. For these paradigms, we further design an association mask in the association module to ensure the consistent interaction between track and detection queries as during inference. Extensive experiments on the nuScenes dataset demonstrate that our approach consistently enhances different tracking methods by only changing the training process, especially the paradigms with explicit association module. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03258 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking Ding, Shuxiao Yang, Yutong Wiederer, Julian Braun, Markus Li, Peizheng Gall, Juergen Yang, Bin Computer Vision and Pattern Recognition Query denoising has become a standard training strategy for DETR-based detectors by addressing the slow convergence issue. Besides that, query denoising can be used to increase the diversity of training samples for modeling complex scenarios which is critical for Multi-Object Tracking (MOT), showing its potential in MOT application. Existing approaches integrate query denoising within the tracking-by-attention paradigm. However, as the denoising process only happens within the single frame, it cannot benefit the tracker to learn temporal-related information. In addition, the attention mask in query denoising prevents information exchange between denoising and object queries, limiting its potential in improving association using self-attention. To address these issues, we propose TQD-Track, which introduces Temporal Query Denoising (TQD) tailored for MOT, enabling denoising queries to carry temporal information and instance-specific feature representation. We introduce diverse noise types onto denoising queries that simulate real-world challenges in MOT. We analyze our proposed TQD for different tracking paradigms, and find out the paradigm with explicit learned data association module, e.g. tracking-by-detection or alternating detection and association, benefit from TQD by a larger margin. For these paradigms, we further design an association mask in the association module to ensure the consistent interaction between track and detection queries as during inference. Extensive experiments on the nuScenes dataset demonstrate that our approach consistently enhances different tracking methods by only changing the training process, especially the paradigms with explicit association module. |
| title | TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.03258 |