Abstract
Bounding-box regression is a popular technique to refine or predict localization boxes in recent object detection approaches. Typically, bounding-box regressors are trained to regress from either region proposals or fixed anchor boxes to nearby bounding boxes of a pre-defined target object classes. This paper investigates whether the technique is generalizable to unseen classes and is transferable to other tasks beyond supervised object detection. To this end, we propose a class-agnostic and anchor-free box regressor, dubbed Universal Bounding-Box Regressor (UBBR), which predicts a bounding box of the nearest object from any given box. Trained on a relatively small set of annotated images, UBBR successfully generalizes to unseen classes, and can be used to improve localization in many vision problems. We demonstrate its effectivenss on weakly supervised object detection and object discovery.
Abstract (translated)
边界盒回归是近年来对象检测方法中一种常用的优化或预测定位盒的技术。通常,边界框回归器被训练为从区域建议或固定锚定框回归到预定义目标对象类的附近边界框。本文研究了该技术是否可推广到未见过的类中,并可转移到监控对象检测之外的其他任务中。为此,我们提出了一个类不可知和无锚框回归器,称为通用边界框回归器(UBBR),它从任何给定的框预测最近对象的边界框。经过对一组相对较小的注释图像的训练,ubbr成功地归纳为未见过的类,并可用于改善许多视觉问题中的本地化。我们证明了它在弱监督目标检测和目标发现方面的有效性。
URL
https://arxiv.org/abs/1904.06805