# MetaAnchor: Learning to Detect Objects with Customized Anchors Source: [MetaAnchor: Learning to Detect Objects with Customized Anchors]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:37.208Z Authors: Tong Yang, Xiangyu Zhang, Zeming Li, Wenqiang Zhang, Jian Sun Published: 2018-07-03T05:20:20.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO v2017 (test-dev)](): Object Detection; COCO v2017 (test-dev); mAP: 45.9. - [Object Detection on MS COCO (test-dev)](): Object Detection; MS COCO (test-dev); mAP@.5: not recorded. ## Original sources and implementation [Original paper]() [PDF]()