Object detection has attracted growing attention due to its extensive application prospect, in which bounding box regression is an essential component. Dedicated to collaborative learning in bounding box regression, we explore the unified framework of smooth ${\ell }_1$ and intersection over union, named SLIoU. On the basis of that, we propose a SLIoU loss as localization loss, which focuses on the geometric relationships of pairs of rectangular bounding boxes in overlapping degree, central position and structural shape. Furthermore, we propose a SLIoU-NMS for suppressing redundant detection boxes, which adaptively maps the evaluation value of detection boxes to meet the evaluation metric using nonlinear representation. By incorporating SLIoU loss and SLIoU-NMS into the state-of-the-art one-stage detectors, the detection performance is considerably improved.

目标检测因其广泛的应用前景而受到越来越多的关注，其中边界框回归是必不可少的组成部分。致力于边界框回归中的协作学习，我们探索了平滑的统一框架${\ell }_1$并在联合上交集，命名为 SLIoU。在此基础上，我们提出了 SLIoU 损失作为定位损失，它侧重于重叠度、中心位置和结构形状的矩形边界框对的几何关系。此外，我们提出了一种用于抑制冗余检测框的 SLIoU-NMS，它自适应地映射检测框的评估值以满足使用非线性表示的评估度量。通过将 SLIoU 损失和 SLIoU-NMS 结合到最先进的一级检测器中，检测性能得到了显着提高。