.png){kind=icon}
返回
A Decoder-Free Variational Deep Embedding for Unsupervised Clustering
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3071275.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In deep clustering frameworks, autoencoder (AE)- or variational AE-based clustering approaches are the most popular and competitive ones that encourage the model to obtain suitable representations and avoid the tendency for degenerate solutions simultaneously. However, for the clustering task, the decoder for reconstructing the original input is usually useless when the model is finished training. The encoder-decoder architecture limits the depth of the encoder so that the learning capacity is reduced severely. In this article, we propose a decoder-free variational deep embedding for unsupervised clustering (DFVC). It is well known that minimizing reconstruction error amounts to maximizing a lower bound on the mutual information (MI) between the input and its representation. That provides a theoretical guarantee for us to discard the bloated decoder. Inspired by contrastive self-supervised learning, we can directly calculate or estimate the MI of the continuous variables. Specifically, we investigate unsupervised representation learning by simultaneously considering the MI estimation of continuous representations and the MI computation of categorical representations. By introducing the data augmentation technique, we incorporate the original input, the augmented input, and their high-level representations into the MI estimation framework to learn more discriminative representations. Instead of matching to a simple standard normal distribution adversarially, we use end-to-end learning to constrain the latent space to be cluster-friendly by applying the Gaussian mixture distribution as the prior. Extensive experiments on challenging data sets show that our model achieves higher performance over a wide range of state-of-the-art clustering approaches.
Keyword:
Clustering algorithms
Data models
Neural networks
Image reconstruction
Decoding
Training
Estimation
Augmented mutual information (MI)
deep clustering
self-supervised learning (SSL)
variational embedding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
Spectrophotometric Determination of Carbon Disulfide Using Bis(4-(4 -Nitrophenyl)azo-2-Nitrophenyl) Disulfide双 (4-硝基苯基) azo-2-Nitrophenyl) 二硫化物分光光度法测定二硫化碳
PREAI
分享收藏Tinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients耳鸣再训练疗法 (TRT) 作为治疗耳鸣和高亢患者的方法
PREAI
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
查看更多内容