FreeAnchor: Learning to Match Anchors for Visual Object Detection
Xiaosong Zhang · Fang Wan · Chang Liu · Rongrong Ji · Qixiang Ye

Wed Dec 11th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #88

Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Unit (IoU). In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner. Our approach, referred to as FreeAnchor, updates hand-crafted anchor assignment to "free" anchor matching by formulating detector training as a maximum likelihood estimation (MLE) procedure. FreeAnchor targets at learning features which best explain a class of objects in terms of both classification and localization. FreeAnchor is implemented by optimizing detection customized likelihood and can be fused with CNN-based detectors in a plug-and-play manner. Experiments on COCO demonstrate that FreeAnchor consistently outperforms the counterparts with significant margins.

Author Information

Xiaosong Zhang (University of Chinese Academy of Sciences)
Fang Wan (University of Chinese Academy of Sciences)
Chang Liu (University of Chinese Academy of Sciences)
Rongrong Ji (Xiamen University, China)
Qixiang Ye (University of Chinese Academy of Sciences, China)

More from the Same Authors