Training Support Vector Machines for Dealing with the ImageNet Challenging Problem - Archive ouverte HAL Access content directly
Book Section Year : 2021

Training Support Vector Machines for Dealing with the ImageNet Challenging Problem

Abstract

We propose the parallel multi-class support vector machines (Para-SVM) algorithm to efficiently perform the classification task of the ImageNet challenging problem with very large number of images and a thousand classes. Our Para-SVM learns in the parallel way to create ensemble binary SVM classifiers used in the One-Versus-All multi-class strategy. The stochastic gradient descent (SGD) algorithm rapidly trains the binary SVM classifier from mini-batches being created by under-sampling training dataset. The numerical test results on ImageNet challenging dataset show that the Para-SVM algorithm is faster and more accurate than the state-of-the-art SVM algorithms. Our Para-SVM achieves an accuracy of 74.89% obtained in the classification of ImageNet-1000 dataset having 1,261,405 images in 2048 deep features into 1,000 classes in 53.29 min using a PC Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores.
Not file

Dates and versions

hal-03565149 , version 1 (10-02-2022)

Identifiers

Cite

Thanh-Nghi Do, Hoai An Le Thi. Training Support Vector Machines for Dealing with the ImageNet Challenging Problem. Modelling, Computation and Optimization in Information Systems and Management Sciences : proceedings of the 4th International Conference on Modelling, Computation and Optimization in Information Systems and Management Sciences - MCO 2021, 363, Springer International Publishing, pp.235-246, 2021, Lecture Notes in Networks and Systems, 978-3-030-92666-3, 978-3-030-92665-6. ⟨10.1007/978-3-030-92666-3_20⟩. ⟨hal-03565149⟩
32 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More