Representation learning via a semi-supervised stacked distance autoencoder for image classification

Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reducti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Frontiers of information technology & electronic engineering Ročník 21; číslo 7; s. 1005 - 1018
Hlavní autoři: Hou, Liang, Luo, Xiao-yi, Wang, Zi-yang, Liang, Jun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Hangzhou Zhejiang University Press 01.07.2020
Springer Nature B.V
College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
Témata:
Classification
Communications Engineering
Computer Hardware
Computer Science
Computer Systems Organization and Communication Networks
Datasets
Deep learning
Electrical Engineering
Electronics and Microelectronics
Feature extraction
Image classification
Instrumentation
Machine learning
Networks
Neural networks
Object recognition
Traffic signs
TP391.9
Neural network
Autoencoder
Semi-supervised learning
Image classification
ISSN:2095-9184, 2095-9230
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional autoencoder, incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance autoencoder. Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic autoencoder structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance autoencoder method is compared with the traditional autoencoder, sparse autoencoder, and supervised autoencoder. Experimental results verify the effectiveness of the proposed model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2095-9184
2095-9230
DOI:10.1631/FITEE.1900116