FreeAnchor: Learning to Match Anchors for Visual Object Detection

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 their counterparts with significant margins.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO test-dev FreeAnchor (ResNeXt-101) box mAP 44.8 # 136
AP50 64.3 # 87
AP75 48.4 # 89
APS 27 # 76
APM 47.9 # 76
APL 56 # 91
Hardware Burden None # 1
Operations per network pass None # 1

Methods