作为极端点的物体 (Objects as Extreme Points)

Object detection can be regarded as a pixel clustering task, and its boundary is determined by four extreme points (leftmost, top, rightmost, and bottom). However, most studies focus on the center or corner points of the object, which are actually conditional results of the extreme points. In this paper, we present an Extreme-Point-Prediction-Based object detector (EPP-Net), which directly regresses the relative displacement vector between each pixel and the four extreme points. We also propose a new metric to measure the similarity between two groups of extreme points, namely, Extreme Intersection over Union (EIoU), and incorporate this EIoU as a new regression loss. Moreover, we propose a novel branch to predict the EIoU between the ground-truth and the prediction results, and combine it with the classification confidence as the ranking keyword in non-maximum suppression. On the MS-COCO dataset, our method achieves an average precision (AP) of 44.0% with ResNet-50 and an AP of 48.3% with ResNeXt-101-DCN. The proposed EPP-Net provides a new method to detect objects and outperforms state-of-the-art anchor-free detectors.

翻译：对象检测可被视为像素群集任务,其边界由四组极端点(最左、最上、最右和最下)确定。然而,大多数研究侧重于对象的中心或角点,这些点实际上是极端点的有条件结果。在本文中,我们提出了一个极端点定位天体探测器(EPP-Net),它直接回归了每个像素和四个极端点之间的相对移位矢量。我们还提出了衡量两组极端点之间相似性的新指标,即Union(EIOU)的极端交叉点,并将EIOU作为新的回归损失纳入其中。此外,我们提出了一个新的分支,以预测地壳与预测结果之间的EIOU,并将之与作为非最大抑制的排序关键点的分类信任结合起来。在MS-COCO数据集中,我们的方法实现了44.0%的平均精确度(AP),ResNet-50和AP48.3%的平均精确度(AP)与ResNeXt-101-DCN。提议的EP-Net 安全级探测器提供了一种新的检测方法,以检测状态和状态。