.png){kind=icon}
返回
Self-supervised deep subspace clustering with entropy-norm
.png){kind=icon}
PRE
AI
DOI：10.1007/s10586-023-04033-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Auto-Encoder based Deep Subspace Clustering (DSC) has been widely applied in computer vision, motion segmentation and image processing. However, existing DSC methods suffer from two limitations: (1) they ignore the rich useful relational information and the connectivity within each subspace due to the reconstruction loss; (2) they design convolutional networks individually according to specific datasets. To address the above problems and improve the performance of DSC, we propose a novel algorithm called Self-Supervised deep Subspace Clustering with Entropy-norm((SCE)-C-3) in this paper. Firstly, (SCE)-C-3 introduces self-supervised contrastive learning to pre-train the encoder instead of requiring a decoder. Besides, the trained encoder is used as a feature extractor to segment subspace by combining self-expression layer and entropy-norm constraint. This not only preserves the local structure of data, but also improves the connectivity between data points. Extensive experimental results demonstrate the superior performance of (SCE)-C-3 in comparison to the state-ofthe-art approaches.
Keyword:
Deep subspace clustering
Self-supervise
Contrastive learning
Entropy-norm
期刊
C
IF:
4.1
论文数:
5.1K
被引数:
7.5K
机构
引用论文
Abstract 22: Late Functional Improvement in Acute Ischemic Stroke Patients: Pooled Analysis of Three Multicenter Clinical Trials.png)
Stroke
StrokeIF0
PREAI
分享收藏
查看更多内容