中国科学院大学学报2024，Vol.41Issue(3)：411-426,16.DOI:10.7523/j.ucas.2023.013
不平衡样本下的SA-YOLO自适应损失目标检测算法
SA-YOLO:self-adaptive loss object detection method under imbalance samples
摘要
Abstract
The phenomenon of sample imbalance refers to the excessive number of background easy samples in the dataset but too few foreground hard samples,which means the sample suffers from inter-class imbalance and hard-easy imbalance.Most of the existing object detection methods are two-stage detectors based on proposed regions or one-stage detectors based on regression.When applied to imbalanced samples,it is impossible to avoid the over-dependence of the prediction bounding box generated in training on a large number of negative samples,which leads to overfitting of the model and low detection accuracy,poor accuracy and generalization.In order to achieve efficient and accurate object detection under imbalanced samples,a new SA-YOLO self-adaptive loss object detection method is proposed in the paper.1)To address the sample imbalance problem,we propose the SA-Focal Loss function,which adjusts the loss adaptively for different datasets and training stages to balance inter-class samples and hard-easy samples.2)In this paper,we construct the CSPDarknet53-SP network architecture based on the multi-scale feature prediction mechanism,which enhances the extraction ability of global features of difficult small target samples and improves the detection accuracy of difficult samples.To verify the performance of the SA-YOLO method,extensive simulation experiments are conducted on the sample imbalance dataset and the COCO dataset respectively.The results show that compared with the optimal metrics of YOLO series method,SA-YOLO reaches 91.46%of mAP in the imbalance dataset,which improves 10.87%,and the enhancement of AP50 for all kinds of objects is more than 2%,with excellent specialization;mAP50 in the COCO dataset is upgraded by 1.58%,and all indexes are not lower than the optimal value,with good effectiveness.关键词
不平衡样本/自适应损失/SA-YOLO算法/SA-Focal Loss函数/CSPDarknet53-SP 网络架构Key words
imbalanced sample/self-adaptive loss/SA-YOLO algorithm/SA-Focal Loss function/CSPDarknet53-SP network architecture分类
信息技术与安全科学引用本文复制引用
苏亚鹏,陈高曙,赵彤..不平衡样本下的SA-YOLO自适应损失目标检测算法[J].中国科学院大学学报,2024,41(3):411-426,16.基金项目
国家自然科学基金(12271504,11991022)资助 （12271504,11991022）
