OTA：用于目标检测的最优传输分配
OTA: Optimal Transport Assignment for Object Detection
摘要：
目标检测中标签分配的最新进展主要是寻求独立地定义每个地面实况（gt）对象的正/负训练样本。在本文中，我们创新性地重新审视标签分配从全球的角度来看，并提出制定分配过程作为一个最优运输（OT）问题-一个很好的研究课题，在优化理论。具体地说，我们将每对需求者（锚）和供应者（gt）之间的单位运输成本定义为它们的分类和回归损失的加权和。在公式化之后，寻找最佳分配解决方案转换为以最小运输成本求解最优运输计划，可以通过Sinkhorn-Knopp迭代来求解。在COCO上，配备最优传输分配（OTA）的单个FCOS-ResNet-50检测器可以在1X调度器下达到40.7% mAP，优于所有其他现有的分配方法。在COCO和CrowdHuman上进行的大量实验进一步验证了我们提出的OTA的有效性，特别是在人群场景中的优越性。该代码可在https://github.com/Megvii-BaseDetection/OTA上获得。
英文摘要：
Recent advances in label assignment in object detection mainly seek to independently define positive/negative training samples for each ground-truth (gt) object. In this paper, we innovatively revisit the label assignment from a global perspective and propose to formulate the assigning procedure as an Optimal Transport (OT) problem -- a well-studied topic in Optimization Theory. Concretely, we define the unit transportation cost between each demander (anchor) and supplier (gt) pair as the weighted summation of their classification and regression losses. After formulation, finding the best assignment solution is converted to solve the optimal transport plan at minimal transportation costs, which can be solved via Sinkhorn-Knopp Iteration. On COCO, a single FCOS-ResNet-50 detector equipped with Optimal Transport Assignment (OTA) can reach 40.7% mAP under 1X scheduler, outperforming all other existing assigning methods. Extensive experiments conducted on COCO and CrowdHuman further validate the effectiveness of our proposed OTA, especially its superiority in crowd scenarios. The code is available at https://github.com/Megvii-BaseDetection/OTA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
