典型文献
Multi-granularity semantic alignment distillation learning for remote sensing image semantic segmentation
文献摘要：
1 Introduction
Due to the powerful feature extraction ability of convolutional neural network[1],deep model-based semantic segmentation of remote sensing images have received more and more attention.The large-scale deep networks bring greater computational complexity[2].However,deploying deep semantic segmentation models on devices with limited resources and high real-time requirements is challenging.Therefore,how to reduce the size of model parameters while maintaining the segmentation performance has become a problem in the practical application of remote sensing image semantic segmentation methods.
文献关键词：
中图分类号：
作者姓名：
Di ZHANG;Yong ZHOU;Jiaqi ZHAO;Zhongyuan YANG;Hui DONG;Rui YAO;Huifang MA
作者机构：
School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116,China;Engineering Research Center of Mine Digitization,Ministry of Education of the People's Republic of China,Xuzhou 221116,China;College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070,China
文献出处：
引用格式：
[1]Di ZHANG;Yong ZHOU;Jiaqi ZHAO;Zhongyuan YANG;Hui DONG;Rui YAO;Huifang MA-.Multi-granularity semantic alignment distillation learning for remote sensing image semantic segmentation)[J].计算机科学前沿,2022(04):229-231
A类：
B类：
Multi,granularity,semantic,alignment,distillation,learning,remote,sensing,segmentation,Introduction,
Due,powerful,feature,extraction,ability,convolutional,neural,deep,images,have,received,more,attention,large,scale,networks,bring,greater,computational,complexity,However,deploying,models,devices,limited,resources,high,real,requirements,challenging,Therefore,how,reduce,size,parameters,while,maintaining,performance,has,become,problem,practical,application,methods
AB值：
0.637615
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
