Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases

TL;DR

This paper introduces a simple yet effective method for fast retrieval of visual descriptors in large-scale databases using compact hash codes derived from multiple k-means assignment, outperforming more complex methods.

Contribution

The paper proposes a novel compact hashing technique based on multiple k-means assignment for efficient visual descriptor retrieval in large datasets.

Findings

High retrieval performance on datasets up to one billion descriptors

Outperforms more complex state-of-the-art methods

Effective on both local and global visual content descriptors

Abstract

In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment. The method has been applied to the problem of approximate nearest neighbor (ANN) search of local and global visual content descriptors, and it has been tested on different datasets: three large scale public datasets of up to one billion descriptors (BIGANN) and, supported by recent progress in convolutional neural networks (CNNs), also on the CIFAR-10 and MNIST datasets. Experimental results show that, despite its simplicity, the proposed method obtains a very high performance that makes it superior to more complex state-of-the-art methods.