Local Deep-Feature Alignment for Unsupervised Dimension Reduction

This paper presents an unsupervised deep-learning framework named local deep-feature alignment (LDFA) for dimension reduction. We construct neighbourhood for each data sample and learn a local stacked contractive auto-encoder (SCAE) from the neighbourhood to extract the local deep features. Next, we...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing Jg. 27; H. 5; S. 2420 - 2432
Hauptverfasser: Zhang, Jian, Yu, Jun, Tao, Dacheng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.05.2018
Schlagworte:
auto-encoder
Deep learning
dimension reduction
Dimensionality reduction
Feature extraction
global alignment
Image reconstruction
Learning systems
locality preserving
Manifolds
Principal component analysis
ISSN:1057-7149, 1941-0042, 1941-0042
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents an unsupervised deep-learning framework named local deep-feature alignment (LDFA) for dimension reduction. We construct neighbourhood for each data sample and learn a local stacked contractive auto-encoder (SCAE) from the neighbourhood to extract the local deep features. Next, we exploit an affine transformation to align the local deep features of each neighbourhood with the global features. Moreover, we derive an approach from LDFA to map explicitly a new data sample into the learned low-dimensional subspace. The advantage of the LDFA method is that it learns both local and global characteristics of the data sample set: the local SCAEs capture local characteristics contained in the data set, while the global alignment procedures encode the interdependencies between neighbourhoods into the final low-dimensional feature representations. Experimental results on data visualization, clustering, and classification show that the LDFA method is competitive with several well-known dimension reduction techniques, and exploiting locality in deep learning is a research topic worth further exploring.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2018.2804218