Laplacian Eigenmaps for dimensionality reduction and data representation
Neural Computation
A fast learning algorithm for deep belief nets
Neural Computation
Relative-Error $CUR$ Matrix Decompositions
SIAM Journal on Matrix Analysis and Applications
NUS-WIDE: a real-world web image database from National University of Singapore
Proceedings of the ACM International Conference on Image and Video Retrieval
Learning Deep Architectures for AI
Foundations and Trends® in Machine Learning
MSRA-MM 2.0: A Large-Scale Web Multimedia Dataset
ICDMW '09 Proceedings of the 2009 IEEE International Conference on Data Mining Workshops
| Hi-index | 0.00 |
Reducing the dimensionality of image with high-dimensional feature plays a significant role in image retrieval and classification. Recently, two methods have been proposed to improve the efficiency and accuracy of dimensionality reduction, one uses CUR matrix decompositions to construct low rank matrix approximations and another approach for dimension reduction trains an auto-encoder with deep architecture to learn low-dimensional codes. In this paper, after above two mentioned methods are respectively utilized to reduce the high-dimensional features of images, we train individual classifiers on both original and reduced feature space for image classification. This paper compares these two approaches with other approaches in image classification. At the same, we also study the effects of the depth of layers on the performance of dimensionality reduction using auto-encoder.