纠正多视角目标关联中评估指标与实际任务的不匹配问题
Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
- 用Sinkhorn归一化改进评估流程，解决排名指标与分配目标的不一致
- 优化排名指标后，分配准确率未提升，证明指标存在根本性偏差
- 适合关注多摄像头目标跟踪评估可靠性的研究者参考
多视角目标关联是多摄像头感知任务的核心计算机视觉问题。尽管该任务本质上应为一对一匹配，但近期工作主要依赖如AP和FPR-95等成对排名指标进行模型评估。我们指出这些指标与实际分配目标之间存在根本性不匹配。理论上，我们证明即使分配已正确，AP和FPR-95仍可能不完美；而通过Sinkhorn-based归一化可使其达到完美。反之，最优的成对排名仍可能导致错误分配。我们在实践中通过基于Sinkhorn的归一化作为可控后处理压力测试验证了这一不匹配。结果表明，仅调整少数后处理参数即可显著提升AP和FPR-95，但分配级指标（如ACC和IPAA）并无相应改善。
原文摘要 · Abstract (English)
Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained one-to-one matching problem, recent works heavily rely on pairwise ranking metrics like AP and FPR-95 for model evaluation. We highlight a fundamental mismatch between these metrics and the actual assignment objective. Theoretically, we show that AP and FPR-95 can be imperfect even when the assignment is already correct, and that Sinkhorn-based normalization can make them perfect. Conversely, optimal pairwise ranking can still lead to incorrect assignments. We validate this mismatch in practice by using our Sinkhorn-based normalization as a controlled post-processing stress test. We show that optimizing just a few post-processing parameters significantly boosts AP and FPR-95 without corresponding improvements in assignment-level metrics such as ACC and IPAA.
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。