.png){kind=icon}
返回
A Survey on Deep Semi-Supervised Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TKDE.2022.3220219.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep semi-supervised learning is a fast-growing field with a range of practical applications. This paper provides a comprehensive survey on both fundamentals and recent advances in deep semi-supervised learning methods from perspectives of model design and unsupervised loss functions. We first present a taxonomy for deep semi-supervised learning that categorizes existing methods, including deep generative methods, consistency regularization methods, graph-based methods, pseudo-labeling methods, and hybrid methods. Then we provide a comprehensive review of 60 representative methods and offer a detailed comparison of these methods in terms of the type of losses, architecture differences, and test performance results. In addition to the progress in the past few years, we further discuss some shortcomings of existing methods and provide some tentative heuristic solutions for solving these open problems.
Keyword:
Deep semi-supervised learning
semi-supervised learning
deep learning
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
.png){kind=icon}
Passive signal propagation and membrane properties in median photoreceptors of the giant barnacle
OAAI
OAAI分享收藏EnAET: A Self-Trained Framework for Semi-Supervised and Supervised Learning With Ensemble TransformationsEnAET: 一个自我训练的框架，用于集成转换的半监督和监督学习OAAI
OAAI分享收藏
查看更多内容