|Tong Yang||Megvii(Face++),Fudan University|
|Xiangyu Zhang||Megvii Inc (Face++)|
|Zeming Li||Megvii(Face++) Inc|
|Wenqiang Zhang||Fudan University|
|Jian Sun||Megvii, Face++|
The authors propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks.
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 the transfer task. Our experiment on COCO detection task shows MetaAnchor consistently outperforms the counterparts in various scenarios.