Deep Randomized Ensembles for Metric Learning

TL;DR

This paper introduces a fast, ensemble-based method for learning embedding functions using random label bagging, significantly improving image retrieval performance across multiple datasets.

Contribution

It presents a novel ensemble approach for metric learning that enhances retrieval accuracy by combining multiple randomly trained embedding functions.

Findings

Improved image retrieval results on multiple datasets

Effective embedding functions created by label bagging

Ensemble approach outperforms existing methods

Abstract

Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results. Each embedding function is learned by randomly bagging the training labels into small subsets. We show experimentally that these embedding ensembles create effective embedding functions. The ensemble output defines a metric space that improves state of the art performance for image retrieval on CUB-200-2011, Cars-196, In-Shop Clothes Retrieval and VehicleID.