.png){kind=icon}
返回
Self-Supervised Representation Learning: Introduction, advances, and challenges
.png){kind=icon}
OA
AI
DOI：10.1109/MSP.2021.3134634.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Self-supervised representation learning (SSRL) methods aim to provide powerful, deep feature learning without the requirement of large annotated data sets, thus alleviating the annotation bottleneck-one of the main barriers to the practical deployment of deep learning today. These techniques have advanced rapidly in recent years, with their efficacy approaching and sometimes surpassing fully supervised pretraining alternatives across a variety of data modalities, including image, video, sound, text, and graphs. This article introduces this vibrant area, including key concepts, the four main families of approaches and associated state-of-the-art techniques, and how self-supervised methods are applied to diverse modalities of data. We further discuss practical considerations including workflows, representation transferability, and computational cost. Finally, we survey major open challenges in the field, that provide fertile ground for future work.
Keyword:
Representation learning
Deep learning
Annotations
Computational efficiency
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏The orthologous Tbx transcription factors Omb and TBX2 induce epithelial cell migration and extrusionin vivowithout involvement of matrix metalloproteinases.png)
OncotargetOAAI
OncotargetIF0
OAAI分享收藏
查看更多内容