郑州大学学报（理学版）2024，Vol.56Issue(1)：32-39,8.DOI:10.13705/j.issn.1671-6841.2022210
多尺度融合卷积的轻量化Transformer无人机地物识别模型
A Lightweight Transformer UAV Surface Feature Recognition Model Based on Multi-scale Fusion Convolutional Networks
摘要
Abstract
The Transformer model had excellent performance,but its tremendous number of parameters made it unsuitable for UAV remote sensing mission with limited resources.Therefore,a lightweight Transformer model for multi-scale fusion convolution networks of UAV remote sensing images was pro-posed,and three optimization strategies were designed to improve the accuracy and reduce the number of model parameters.Firstly,a lightweight multi-scale fusion convolution method was designed to supple-ment the intra-block spatial information lost by Transformer,so as to effectively extract the coarse and fine grained feature representation at multiple scales.Secondly,a multi-scale key-value sequence reduction method was devised to optimize the self-attention calculation in Transformer.Finally,a lightweight MLP decoder was applied to further reduce the number of model parameters.The comparative experiments with some mainstream models on Vaihingen and Potsdam data sets showed that the F1 value and intersection over union of the proposed model were improved.Meanwhile,the accuracy of the Potsdam data set was improved by 0.29%,and the parameters were reduced by 18%compared with the dual branch network STransFuse.关键词
无人机遥感影像/Transformer/语义分割/轻量级/多尺度/卷积神经网络Key words
UAV remote sensing image/Transformer/semantic segmentation/lightweight/multi-scale/convolutional neural network分类
信息技术与安全科学引用本文复制引用
肖斌,罗浩,张恒宾,刘宏伟,张兴鹏..多尺度融合卷积的轻量化Transformer无人机地物识别模型[J].郑州大学学报（理学版）,2024,56(1):32-39,8.基金项目
国家自然科学基金项目(62006200) （62006200）
四川省自然科学基金项目(2022YFG0179) （2022YFG0179）
油气藏地质与开发国家重点实验室开放基金项目(成都理工大学)(PLC20211104). （成都理工大学）
