Large-scale image classification using ensembles of nested dichotomies

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.