不依赖外部检测器，用自生成先验提升跟踪精度
SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors
- 用内部自生成检测先验解耦候选框生成与关联
- 在DanceTrack上达69.2 HOTA，BFT上71.1 HOTA
- 适合追求高精度、低依赖的多目标跟踪场景
端到端变压器架构通过将检测与关联统一为无启发式框架，推动了多目标跟踪的进展。然而，检测性能差以及联合架构中检测与关联的固有冲突仍是关键问题。现有方法通过高级去噪或标签分配策略，或引入外部检测器的检测先验来缓解这些问题。本文提出SelfMOTR，一种无需检测器的简洁高效替代方案，通过自生成的内部检测先验解耦提案发现与关联。通过大量分析与消融实验，我们发现端到端变压器跟踪器在联合检测-关联解码中仍保留显著的隐藏检测能力，并提供了一种实用的探测器无关机制加以利用。为揭示这些联合解码动态，我们借鉴大语言模型中的注意力汇分析，利用追踪注意力质量（Track Attention Mass）表明标准通用查询存在注意力不平衡，难以同时权衡轨迹上下文与新目标发现。SelfMOTR在复杂动态环境中表现优异，在DanceTrack上取得69.2 HOTA，在鸟群跟踪（Bird Flock Tracking, BFT）数据集上领先至71.1 HOTA。
原文摘要 · Abstract (English)
End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single, heuristic-free framework. Despite these benefits, poor detection performance and the inherent conflict between detection and association in a joint architecture remain critical concerns. Recent approaches aim to mitigate these issues by employing advanced denoising or label assignment strategies, or by incorporating detection priors from external object detectors. In this paper, we propose SelfMOTR, a simple yet highly effective detector-free alternative that decouples proposal discovery from association using self-generated internal detection priors. Through extensive analysis and ablation studies, we show that end-to-end transformer trackers with joint detection-association decoding retain substantial hidden detection capacity, and we provide a practical detector-free mechanism for leveraging it. To shed light on these joint decoding dynamics, we draw inspiration from attention sink analyses in large language models, leveraging Track Attention Mass to show that standard generic queries exhibit unbalanced attention, frequently struggling to weigh track context against novel object discovery. SelfMOTR achieves highly competitive performance in complex, dynamic environments, yielding 69.2 HOTA on DanceTrack and leading with 71.1 HOTA on the Bird Flock Tracking (BFT) dataset. Project page: https://medem23.github.io/SM
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。