FreeAnchor: Learning to Match Anchors for Visual Object Detection
This work addresses a key bottleneck in object detection for computer vision applications, offering a plug-and-play solution that enhances existing detectors.
The paper tackles the problem of anchor assignment in CNN-based object detectors by proposing FreeAnchor, a learning-to-match approach that replaces hand-crafted IoU restrictions with flexible anchor matching, resulting in significant performance improvements on COCO benchmarks.
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.