Deep adaptive networks for image classification

Authors:
Shusen Zhou;Qingcai Chen;Xiaolong Wang
Affiliations:
Harbin Institute of Technology, Shenzhen, P.R. China;Harbin Institute of Technology, Shenzhen, P.R. China;Harbin Institute of Technology, Shenzhen, P.R. China
Venue:
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Year:
2010

Citing 11
Cited 0

Machine Learning

Machine Learning
Training products of experts by minimizing contrastive divergence

Neural Computation
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
A fast learning algorithm for deep belief nets

Neural Computation
An entropy-based quantum neuro-fuzzy inference system for classification applications

Neurocomputing
Representational power of restricted boltzmann machines and deep belief networks

Neural Computation
Deep networks for image retrieval on large-scale databases

MM '08 Proceedings of the 16th ACM international conference on Multimedia
Exploring Strategies for Training Deep Neural Networks

The Journal of Machine Learning Research
Multi-view multi-label active learning for image classification

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Multiple kernel active learning for image classification

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Learning Deep Architectures for AI

Learning Deep Architectures for AI

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel classifier called Deep Adaptive Networks (DAN) with deep architecture for image classification. First, we construct a deep and directed belief nets using a set of Restricted Boltzmann Machines (RBM) via greedy and layer-wise unsupervised learning. Then, we refine the parameter space of the deep architecture to adapt the classification demand using global gradient-descent based supervised learning. An exponential loss function is utilized to maximize the separability. Experiments on two real-world image datasets show that the proposed classifier outperforms the representative classification techniques and the existing deep learning methods.