典型文献
Connecting the Dots in Self-Supervised Learning:A Brief Survey for Beginners
文献摘要：
The artificial intelligence(AI)community has recently made tremendous progress in developing self-supervised learning(SSL)algorithms that can learn high-quality data representations from massive amounts of unlabeled data.These methods brought great results even to the fields outside of Al.Due to the joint efforts of researchers in various areas,new SSL methods come out daily.However,such a sheer number of publications make it difficult for beginners to see clearly how the subject progresses.This survey bridges this gap by carefully selecting a small portion of papers that we believe are milestones or essential work.We see these researches as the"dots"of SSL and connect them through how they evolve.Hopefully,by viewing the connections of these dots,readers will have a high-level picture of the development of SSL across multiple disciplines including natural language processing,computer vision,graph learning,audio processing,and protein learning.
文献关键词：
中图分类号：
作者姓名：
Peng-Fei Fang;Xian Li;Yang Yan;Shuai Zhang;Qi-Yue Kang;Xiao-Fei Li;Zhen-Zhong Lan
作者机构：
School of Engineering,WestLake University,Hangzhou 310030,China;College of Engineering and Computer Science,Australian National University,Canberra,ACT 2601,Australia;College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China
文献出处：
引用格式：
[1]Peng-Fei Fang;Xian Li;Yang Yan;Shuai Zhang;Qi-Yue Kang;Xiao-Fei Li;Zhen-Zhong Lan-.Connecting the Dots in Self-Supervised Learning:A Brief Survey for Beginners)[J].计算机科学技术学报（英文版）,2022(03):507-526
A类：
Beginners
B类：
Connecting,Dots,Self,Supervised,Learning,Brief,Survey,artificial,intelligence,community,has,recently,made,tremendous,developing,self,supervised,learning,SSL,algorithms,that,can,high,quality,data,representations,from,massive,amounts,unlabeled,These,methods,brought,great,results,even,fields,outside,Due,joint,efforts,researchers,various,areas,new,come,daily,However,such,sheer,number,publications,make,difficult,beginners,see,clearly,how,subject,progresses,This,survey,bridges,this,gap,by,carefully,selecting,small,portion,papers,believe,milestones,essential,work,We,these,researches,dots,them,through,they,evolve,Hopefully,viewing,connections,readers,will,have,level,picture,development,across,multiple,disciplines,including,natural,language,processing,computer,vision,graph,audio,protein
AB值：
0.746025
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。
