摘要
本文提出一种基于特征增强知识蒸馏的目标检测压缩算法(ODCA)。首先,使用坐标注意力增强教师网络中间层特征对前景目标的表征能力;然后,采用二进制掩码在空间上区分前景和背景,并定义带权重的空间信息损失以平衡前景和背景特征蒸馏强度;最后,使用卷积操作统一教师和学生网络通道数,构造通道信息损失学习特征的通道间分布信息。在Pascal VOC数据集上的实验结果表明,所提算法将学生网络的平均精度均值从68.3%提高至75.7%。
An object detection compression algorithm(ODCA)based on feature enhancement knowledge distillation is proposed.Firstly,coordinate attention is used to enhance the representation ability of intermediate layer features of the teacher network for foreground target.Then,binary masks are used to spatially distinguish foreground and background,and a weighted spatial information loss is defined to balance the strength of foreground and background feature distillation.Finally,the convolution operation is used to unify the number of network channels of teachers and students,and the distribution information between channels of the learning features of channel information loss is constructed.Experimental results on the Pascal VOC dataset show that the proposed algorithm improves the mean average precision(mAP)of the student network from 68.3 % to 75.7 %.
作者
邓兴隆
王逸涵
罗建桥
熊鹰
李柏林
DENG Xinglong;WANG Yihan;LUO Jianqiao;XIONG Ying;LI Bailin(School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China)
出处
《传感器与微系统》
CSCD
北大核心
2024年第5期116-120,共5页
Transducer and Microsystem Technologies
基金
四川省科技计划资助项目(重点研发项目)(2021YFN0020)。
