Publication
Large-scale image classification using ensembles of nested dichotomies
Conference Article
Conference
Catalan Conference on Artificial Intelligence (CCIA)
Edition
16th
Pages
87-90
Doc link
http://dx.doi.org/10.3233/978-1-61499-320-9-87
File
Abstract
Many techniques to reduce the cost at test time in large-scale problems involve a hierarchical organization of classifiers, but are either too expensive to learn or degrade the classification performance. Conversely, in this work we show that using ensembles of randomized hierarchical decompositions of the original problem can both improve the accuracy and reduce the computational complexity at test time. The proposed method is evaluated in the ImageNet Large Scale Visual Recognition Challenge’10, with promising results.
Categories
computer vision, image classification.
Author keywords
large-scale image classification, classifier ensembles, ensembles of nested dichotomies
Scientific reference
A. Ramisa and C. Torras. Large-scale image classification using ensembles of nested dichotomies, 16th Catalan Conference on Artificial Intelligence, 2013, Vic, Spain, in Artificial Intelligence Research and Development, Vol 256 of Frontiers in Artificial Intelligence and Applications, pp. 87-90, 2013, IOS Press.
Follow us!