Content-Based Landmark Retrieval Combining Global and Local Features using Siamese Neural Networks

TL;DR

This paper introduces a landmark retrieval method combining global features from a Siamese network with local feature re-ranking, improving search accuracy by leveraging both feature types and dataset augmentation.

Contribution

It proposes a novel approach that integrates global and local features using Siamese networks and cosine similarity for improved landmark retrieval performance.

Findings

Local feature re-ranking enhances retrieval accuracy.

Dataset augmentation improves robustness to intra-class variance.

Global features from Siamese networks provide effective initial ranking.

Abstract

In this work, we present a method for landmark retrieval that utilizes global and local features. A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search. We utilize the extracted feature maps from the Siamese architecture as local descriptors, the search results are then further refined using a cosine similarity between local descriptors. We conduct a deeper analysis of the Google Landmark Dataset, which is used for evaluation, and augment the dataset to handle various intra-class variances. Furthermore, we conduct several experiments to compare the effects of transfer learning and metric learning, as well as experiments using other local descriptors. We show that a re-ranking using local features can improve the search results. We believe that the proposed local feature extraction using cosine similarity is a simple approach that can be extended to many other retrieval tasks.