In the recent years, Convolutional Neural Network-based object detection has experienced impressive progress. Despite these improvements, the performance on the small object detection leaves much to be desired, small objects are often missed or wrongly detected. The reasonable explanation is that the supervisory signals on the small objects are insufficient, and through the analysis of loss distribution over different scales in the iterations, there is a significant gap between the loss provided by the small objects and large objects. In order to balance the loss distribution and alleviate the insufficient supervisory on the small objects, a Feedback-driven loss function is presented in this paper. The Feedback-driven loss function uses the loss distribution information as the feedback signal, compared with the original loss function, the Feedback-driven loss function can supervise small objects more effectively, and train the detectors in a more balanced way. Experiments have been conducted on various detectors, backbones, training periods and datasets. Compared to the current state-of-the-art method, the novel Feedback-driven loss function can achieve 2.3% relative improvement on the Mean Average Precision, and especially 3.5% improvement on the detection of small objects, with nearly no additional computation both in training and testing stages.

近年来，基于卷积神经网络的目标检测取得了令人瞩目的进展。尽管有这些改进，但是在小物体检测方面的性能仍有很多不足之处，经常会遗漏或错误地检测出小物体。合理的解释是，小对象上的监控信号不足，并且通过分析迭代中不同尺度上的损耗分布，在小对象和大对象提供的损耗之间存在很大的差距。为了平衡损失分布并减轻对小物体的监督不足，本文提出了一种反馈驱动的损失函数。与原始损失函数相比，反馈驱动的损失函数将损失分布信息用作反馈信号，反馈驱动的损耗功能可以更有效地监控小物体，并以更加平衡的方式训练探测器。已经对各种检测器，骨干，训练周期和数据集进行了实验。与当前的最新方法相比，新颖的反馈驱动损耗函数可以在噪声抑制方面实现2.3％的相对改进。平均平均精度，尤其是小物体的检测提高了3.5％，在训练和测试阶段几乎没有其他计算。