论文标题
SIOU损失：更强大的学习框回归
SIoU Loss: More Powerful Learning for Bounding Box Regression
论文作者
论文摘要
对象检测的有效性是计算机视觉任务中的主要问题之一，高度取决于损耗函数的定义 - 衡量了ML模型可以预测预期结果的准确度。传统的对象检测损耗函数取决于边界框回归的指标的聚合，例如距离，重叠区域以及预测的真相盒和地面真相框的纵横比（即GIOU，CIOU，ICIOU等）。但是，没有提出和用于日期的方法考虑所需的接地盒与预测的“实验”框之间的不匹配方向。由于预测的框在训练过程中可以“四处徘徊”，并且最终产生了较差的模型，因此这种短缺会导致较慢且效率较低。在本文中，提出了一个新的损失函数SIO，考虑到所需回归之间的向量的角度，重新定义了罚款指标。应用于常规的神经网络和数据集，表明SIO提高了训练速度和推理的准确性。在许多模拟和测试中揭示了提出的损失函数的有效性。
The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function - a measure of how accurately your ML model can predict the expected outcome. Conventional object detection loss functions depend on aggregation of metrics of bounding box regression such as the distance, overlap area and aspect ratio of the predicted and ground truth boxes (i.e. GIoU, CIoU, ICIoU etc). However, none of the methods proposed and used to date considers the direction of the mismatch between the desired ground box and the predicted, "experimental" box. This shortage results in slower and less effective convergence as the predicted box can "wander around" during the training process and eventually end up producing a worse model. In this paper a new loss function SIoU was suggested, where penalty metrics were redefined considering the angle of the vector between the desired regression. Applied to conventional Neural Networks and datasets it is shown that SIoU improves both the speed of training and the accuracy of the inference. The effectiveness of the proposed loss function was revealed in a number of simulations and tests.
