从检测到关联：为多目标跟踪学习判别性目标嵌入
From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
针对端到端 DETR 类跟踪器中共享检测嵌入类间相似度过高的问题，用空间/时序/身份三个适配器在检测特征上做显式精炼，可直接迁移到任何 DETR 式跟踪或关联头中提升跨帧实例判别性。
原文依据 object embeddings produced by the shared DETR architecture display excessively high inter-object similarity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论端到端多目标跟踪（MOT）方法近来通过在单一框架内统一检测与关联取得了显著进展。尽管检测性能强劲，这类方法的关联准确率却相对偏低。通过细致分析，我们发现共享 DETR 架构所产生的目标嵌入呈现出过高的目标间相似度，因为它在单帧内仅强调类别级判别。相比之下，跟踪需要跨帧的、具有空间与时序连续性的实例级区分，而当前端到端方法对目标嵌入的优化并不充分。为此，我们提出 FDTA（From Detection to Association），一个显式的特征精炼框架，从三个互补视角增强目标判别性。具体而言，我们引入空间适配器（SA）以融合深度感知线索来建模空间连续性，引入时序适配器（TA）以聚合历史信息来建模时序依赖，并引入身份适配器（IA）以利用质量感知的对比学习实现实例级可分性。大量实验表明，FDTA 在 DanceTrack、SportsMOT 和 BFT 等多个具有挑战性的 MOT 基准上取得最优性能，凸显了我们所提出的判别性嵌入增强策略的有效性。代码已发布于 https://github.com/Spongebobbbbbbbbbb/FDTA。
英文原文摘要 1496 字符
End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong detection performance, these methods suffer from relatively low association accuracy. Through detailed analysis, we observe that object embeddings produced by the shared DETR architecture display excessively high inter-object similarity, as it emphasizes only category-level discrimination within single frames. In contrast, tracking requires instance-level distinction across frames with spatial and temporal continuity, for which current end-to-end approaches insufficiently optimize object embeddings. To address this, we introduce FDTA (From Detection to Association), an explicit feature refinement framework that enhances object discriminativeness across three complementary perspectives. Specifically, we introduce a Spatial Adapter (SA) to integrate depth-aware cues for spatial continuity, a Temporal Adapter (TA) to aggregate historical information for temporal dependencies, and an Identity Adapter (IA) to leverage quality-aware contrastive learning for instance-level separability. Extensive experiments demonstrate that FDTA achieves state-of-the-art performance on multiple challenging MOT benchmarks including DanceTrack, SportsMOT, and BFT, highlighting the effectiveness of our proposed discriminative embedding enhancement strategy. The code is available at https://github.com/Spongebobbbbbbbbbb/FDTA.