Compared with the improvement of model structure in the field of object detection, the imbalanced problems in the training process have received less attention, but it is also one of the main reasons affecting its performance. We mainly analyze the imbalanced problems that occur in different stages of the network training process and propose a more balanced network called Balanced-RetinaNet, which has three improvements. First, in the feature extraction stage, a multi-scale feature balanced module is proposed to settle the problem in terms of imbalanced feature distribution, that is, the high-level feature lacks spatial information and while the low-level feature lacks semantic information; then, in the object regression stage, an interval-based regression loss is proposed to solve the problem of inaccurate localization caused by the different contributions of different samples to the regression loss; finally, in the object classification stage, an adaptive focal loss is proposed to solve the problem of classification errors caused by the loss of a large number of negative samples overwhelming the overall classification loss. Experiments have proved that by solving the imbalanced problems, the detection accuracy has been significantly improved on the MS COCO dataset.

中文翻译：

---

平衡视网膜网：解决物体检测中的不平衡问题

与目标检测领域模型结构的改进相比，训练过程中的不平衡问题受到了较少的关注，但这也是影响其性能的主要原因之一。我们主要分析在网络训练过程的不同阶段出现的不平衡问题，并提出一个更平衡的网络，称为Balanced-RetinaNet，它具有三个改进。首先，在特征提取阶段，提出了一种多尺度特征平衡模块来解决特征分布不平衡的问题，即高级特征缺少空间信息，而低级特征缺少语义信息。然后，在对象回归阶段，提出了一种基于区间的回归损失，以解决不同样本对回归损失的不同贡献导致的定位不准确的问题。最后，在目标分类阶段，提出了一种自适应焦点损失算法，以解决由于大量负样本的丢失而使总体分类损失不堪重负的分类误差问题。实验证明，通过解决不平衡问题，MS COCO数据集的检测精度得到了显着提高。