Authors:
Niharjyoti Sarangi
and
C. Chandra Sekhar
Affiliation:
Indian Institute of Technology Madras, India
Keyword(s):
Image Annotation, Tensor Deep Stacking Networks, Kernel Deep Convex Networks, Deep Convolutional Network, Deep Learning.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Classification
;
Computational Intelligence
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Kernel Methods
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Object Recognition
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Software Engineering
;
Theory and Methods
Abstract:
Automatically assigning semantically relevant tags to an image is an important task in machine learning. Many
algorithms have been proposed to annotate images based on features such as color, texture, and shape. Success
of these algorithms is dependent on carefully handcrafted features. Deep learning models are widely used to
learn abstract, high level representations from raw data. Deep belief networks are the most commonly used
deep learning models formed by pre-training the individual Restricted Boltzmann Machines in a layer-wise
fashion and then stacking together and training them using error back-propagation. In the deep convolutional
networks, convolution operation is used to extract features from different sub-regions of the images to learn
better representations. To reduce the time taken for training, models that use convex optimization and kernel
trick have been proposed. In this paper we explore two such models, Tensor Deep Stacking Network and
Kernel Deep Convex Network, f
or the task of automatic image annotation. We use a deep convolutional
network to extract high level features from raw images, and then use them as inputs to the convex deep
learning models. Performance of the proposed approach is evaluated on benchmark image datasets.
(More)