Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate the bounding box predictions. The point feature is convenient to use but may lack the explicit border information for accurate localization. In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature. Based on the BorderAlign, we design a novel detection architecture called BorderDet, which explicitly exploits the border information for stronger classification and more accurate localization. With ResNet-50 backbone, our method improves single-stage detector FCOS by 2.8 AP gains (38.6 v.s. 41.4). With the ResNeXt-101-DCN backbone, our BorderDet obtains 50.3 AP, outperforming the existing state-of-the-art approaches. The code is available at (https://github.com/Megvii-BaseDetection/BorderDet).
翻译:高密度物体探测器依靠在正常图像网格上预测物体的滑动窗口范式。 同时,在网点上绘制地貌图,以产生捆绑框预测。点特征便于使用,但可能缺乏明确的边界信息,以便准确定位。在本文中,我们提议建立一个简单而高效的操作员,称为边界定位,从边界的极端点提取“边界特征”,以加强点特征。在边界定位的基础上,我们设计了一个新的探测结构,称为边界设计,明确利用边界信息进行更强有力的分类和更准确的本地化。在ResNet-50主干线下,我们的方法通过2.8 AP收益(38.6 v. s.41.4)改进了单级FCOS探测器。在ResNeXt-101-DCN主干线上,我们的边界Dett获得了50.3 AP,超过了现有的“最先进”方法。该代码可在(https://github.com/Megvii-Basedrol Dett)查阅。