Deep metric learning using Triplet network

TL;DR

This paper introduces the triplet network, a deep learning model designed to learn semantic data representations through distance comparisons, outperforming Siamese networks in various datasets.

Contribution

The paper presents the triplet network model, a novel approach for learning representations via triplet-based distance comparisons, improving upon existing Siamese network methods.

Findings

Triplet network outperforms Siamese network on multiple datasets.

The model effectively learns semantic representations through distance comparisons.

Potential for future unsupervised learning applications.

Abstract

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. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.