基于相邻特征融合与特征解耦的一阶段目标检测  

One-stage object detection based on adjacent feature fusion and feature decoupling

作　　者：郑剑[1] 贺朝辉 于祥春 ZHENG Jian;HE Zhaohui;YU Xiangchun(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学信息工程学院,赣州341000

出　　处：《北京航空航天大学学报》2025年第4期1205-1214,共10页Journal of Beijing University of Aeronautics and Astronautics

基　　金：江西省自然科学基金(20224BAB212013)。

摘　　要：针对目标检测中特征金字塔网络(FPN)造成的大尺度目标检测精度下降及目标检测2个子任务所需语义特征不一致问题,提出一种基于相邻特征融合(AFF)与特征解耦的网络(AFFDN)模型。该模型中的AFF模块通过多对一连接引入更短的梯度回传路径,缓解了大尺度目标梯度消失的问题;AFF模块通过共享参数和偏移量,有效减小了模型参数量,并增强了多尺度特征语义一致性;相比于基于神经架构搜索的FPN(NAS-FPN),AFF参数量更小、性能增益更显著。AFFDN模型中的特征解耦模块(FDM)通过动态感受野和全局注意力,在感受野-通道-空间3个维度上进行细粒度特征解耦,为不同分支生成特有的任务相关特征,进而提高目标检测精度。将AFFDN模型应用到不同的一阶段目标检测模型时,在PASCAL VOC和MS COCO2017数据集上与基线模型相比,检测精度分别提升了至少0.9%和2.3%。In view of reduced large-scale object detection accuracy caused by the feature pyramid network(FPN)in object detection and the inconsistency of the semantic characteristics of the two sub-tasks of object detection,a new model based on adjacent feature fusion(AFF)and feature decoupling network(AFFDN)model was proposed.Firstly,the AFF module in the model introduced a shorter gradient return path by using the many-to-one connection,thereby alleviating the problem of large-scale object gradient disappearance.At the same time,AFF effectively reduced the amount of model parameters and enhanced the semantic consistency of multi-scale features by sharing parameters and offsets.In addition,compared with neural architecture search FPN(NAS-FPN),the parameters of AFF were smaller,and the performance gain was more significant.Secondly,the feature decoupling module(FDM)in the AFFDN used the dynamic receptive field and global attention to decouple fine-grained features in the three dimensions of receptive field,channel,and space,generating unique task-related features for different task branches and thereby improving the accuracy of object detection.Finally,when AFFDN was applied to different one-stage object detection models,the detection accuracy of the baseline model was improved by at least 0.9%and 2.3%on the PASCAL VOC dataset and MS COCO2017 dataset,respectively.

关 键 词：目标检测 多尺度特征融合 特征解耦 注意力 可变形卷积 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]