Scalable Similarity Learning using Large Margin Neighborhood Embedding

TL;DR

This paper introduces a scalable image similarity learning method that leverages local neighborhood embedding and ensemble projections, enabling efficient large-scale image classification with competitive accuracy.

Contribution

The paper proposes a novel large margin neighborhood embedding approach with ensemble projections for scalable similarity learning on massive image datasets.

Findings

Achieves high recognition accuracy on datasets with up to one million images.

Demonstrates significant efficiency and scalability improvements over existing methods.

Validates effectiveness through experiments on multiple large-scale datasets.

Abstract

Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown promising results, especially when they are underpinned by a learned distance or similarity measurement. Although metric learning has been well studied in the past decades, most existing algorithms are impractical to handle large-scale data sets. In this paper, we present an image similarity learning method that can scale well in both the number of images and the dimensionality of image descriptors. To this end, similarity comparison is restricted to each sample's local neighbors and a discriminative similarity measure is induced from large margin neighborhood embedding. We also exploit the ensemble of projections so that high-dimensional features can be processed in a set of lower-dimensional subspaces in parallel without much performance compromise. The similarity function is learned online using a stochastic gradient descent algorithm in which the triplet sampling strategy is customized for quick convergence of classification performance. The effectiveness of our proposed model is validated on several data sets with scales varying from tens of thousands to one million images. Recognition accuracies competitive with the state-of-the-art performance are achieved with much higher efficiency and scalability.