Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the Triplet network model, which aims to learn useful representations by distance comparisons. We show promising results demonstrating the success of this model on the Cifar10 image dataset. We also discuss future possible usages as a framework for unsupervised learning.
View on arXiv