AE2-Nets: Autoencoder in Autoencoder Networks

Learning on data represented with multiple views (e.g., multiple types of descriptors or modalities) is a rapidly growing direction in machine learning and computer vision. Although effectiveness achieved, most existing algorithms usually focus on classification or clustering tasks. Differently, in...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 2572 - 2580
Hlavní autoři: Zhang, Changqing, Liu, Yeqing, Fu, Huazhu
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2019
Témata:
Autoencoders
Computer vision
Data mining
Data models
Degradation
Encoding
Feature extraction
Machine learning algorithms
Neural networks
Representation learning
Statistical Learning
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Learning on data represented with multiple views (e.g., multiple types of descriptors or modalities) is a rapidly growing direction in machine learning and computer vision. Although effectiveness achieved, most existing algorithms usually focus on classification or clustering tasks. Differently, in this paper, we focus on unsupervised representation learning and propose a novel framework termed Autoencoder in Autoencoder Networks (AE^2-Nets), which integrates information from heterogeneous sources into an intact representation by the nested autoencoder framework. The proposed method has the following merits: (1) our model jointly performs view-specific representation learning (with the inner autoencoder networks) and multi-view information encoding (with the outer autoencoder networks) in a unified framework; (2) due to the degradation process from the latent representation to each single view, our model flexibly balances the complementarity and consistence among multiple views. The proposed model is efficiently solved by the alternating direction method (ADM), and demonstrates the effectiveness compared with state-of-the-art algorithms.
ISSN:1063-6919
DOI:10.1109/CVPR.2019.00268