We propose a novel and flexible anchor mechanism named MetaAnchor for object
detection frameworks. Unlike many previous detectors model anchors via a
predefined manner, in MetaAnchor anchor functions could be dynamically
generated from the arbitrary customized prior boxes. Taking advantage of weight
prediction, MetaAnchor is able to work with most of the anchor-based object
detection systems such as RetinaNet. Compared with the predefined anchor
scheme, we empirically find that MetaAnchor is more robust to anchor settings
and bounding box distributions; in addition, it also shows the potential on
transfer tasks. Our experiment on COCO detection task shows that MetaAnchor
consistently outperforms the counterparts in various scenarios.

本文提出了一种名为 MetaAnchor 的新型灵活的锚点机制，它能够从任意自定义的优先框生成锚点函数，并利用权重预测，能够与大部分锚点有关的对象检测系统（例如 RetinaNet）一起使用，并且在锚点设置和边界框分布方面要比预定义的锚点计划更加强韧，同时还具有转移任务的潜力。我们在 COCO 检测任务上的实验证明，MetaAnchor 在各种情况下始终优于其他对照组。