Please use this identifier to cite or link to this item:
https://dspace.ctu.edu.vn/jspui/handle/123456789/5077
Title: | Parallel multiclass stochastic gradient descent algorithms for classifying million images with very-high-dimensional signatures into thousands classes |
Authors: | Đỗ, Thanh Nghị |
Keywords: | Support vector machine Stochastic gradient descent Multiclass Parallel algorithm Large-scale image classification |
Issue Date: | 2014 |
Series/Report no.: | Vietnam Journal of Computer Science;1 .- p.107-115 |
Abstract: | The new parallel multiclass stochastic gradient descent algorithms aim at classifying million images with very-high-dimensional signatures into thousands of classes. We extend the stochastic gradient descent (SGD) for support vector machines (SVM-SGD) in several ways to develop the new multiclass SVM-SGD for efficiently classifying large image datasets into many classes. We propose (1) a balanced training algorithm for learning binary SVM-SGD classifiers, and (2) a parallel training process of classifiers with several multi-core computers/grid. The evaluation on 1000 classes of ImageNet, ILSVRC 2010 shows that our algorithm is 270 times faster than the state-of-the-art linear classifier LIBLIN-EAR. |
URI: | http://localhost:8080//jspui/handle/123456789/5077 |
Appears in Collections: | Tạp chí quốc tế |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
_file_ | 544.52 kB | Adobe PDF | View/Open | |
Your IP: 3.144.248.24 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.