典型文献
S2-Net:Self-Supervision Guided Feature Representation Learning for Cross-Modality Images
文献摘要：
Dear Editor, This letter focuses on combining the respective advantages of cross-modality images which can compensate for the lack of infor-mation in the single modality.Meanwhile,due to the great appea-rance differences between cross-modality image pairs,it often fails to make the feature representations of correspondences as close as pos-sible.In this letter,we design a cross-modality feature represen-tation learning network,S2-Net,which is based on the recently suc-cessful detect-and-describe pipeline,originally proposed for visible images but adapted to work with cross-modality image pairs.Exten-sive experiments show that our elegant formulation of combined optimization of supervised and self-supervised learning outperforms state-of-the-arts on three cross-modal datasets.
文献关键词：
中图分类号：
作者姓名：
Shasha Mei;Yong Ma;Xiaoguang Mei;Jun Huang;Fan Fan
作者机构：
The authors are with the Electronic Information School,Wuhan University,Wuhan 430072,China
文献出处：
引用格式：
[1]Shasha Mei;Yong Ma;Xiaoguang Mei;Jun Huang;Fan Fan-.S2-Net:Self-Supervision Guided Feature Representation Learning for Cross-Modality Images)[J].自动化学报（英文版）,2022(10):1883-1885
A类：
appea,rance
B类：
S2,Net,Self,Supervision,Guided,Feature,Representation,Learning,Cross,Modality,Images,Dear,Editor, This,letter,focuses,combining,respective,advantages,cross,modality,images,which,can,compensate,lack,infor,mation,single,Meanwhile,due,great,differences,between,pairs,often,fails,make,feature,representations,correspondences,close,In,this,design,learning,network,recently,suc,cessful,detect,describe,pipeline,originally,proposed,visible,but,adapted,Exten,sive,experiments,show,that,our,elegant,formulation,combined,optimization,supervised,self,outperforms,state,arts,three,datasets
AB值：
0.634363
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。
