论文标题
本地化以对本地化进行分类和分类：对象检测中的相互指导
Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
论文作者
论文摘要
大多数深度学习的对象探测器基于锚固机制，并诉诸于预定义的锚点和地面真相盒之间的联合（iou）的交集，以评估锚和物体之间的匹配质量。在本文中，我们质疑IOU的使用，并提出了一个新的锚匹配标准，在训练阶段，通过优化本地化和分类任务来指导：与一个任务相关的预测用于动态分配样品锚点并改善其他任务的模型，以及VISTA。尽管提出的方法很简单，但我们对Pascal VOC和Coco数据集的不同最先进的深度学习体系结构进行了实验，证明了我们相互指导策略的有效性和一般性。
Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In this paper, we question this use of IoU and propose a new anchor matching criterion guided, during the training phase, by the optimization of both the localization and the classification tasks: the predictions related to one task are used to dynamically assign sample anchors and improve the model on the other task, and vice versa. Despite the simplicity of the proposed method, our experiments with different state-of-the-art deep learning architectures on PASCAL VOC and MS COCO datasets demonstrate the effectiveness and generality of our Mutual Guidance strategy.
