# Aggregated Deep Local Features for Remote Sensing Image Retrieval

## TL;DR

This paper introduces a novel image retrieval method for remote sensing images that uses attentive local features aggregated with VLAD, achieving state-of-the-art results without training and with efficient computation.

## Contribution

The paper presents a new retrieval pipeline utilizing attentive local features and VLAD aggregation, along with a training-free query expansion and dimensionality reduction techniques.

## Key findings

- Outperforms existing systems without training.
- Query expansion improves performance by about 3%.
- Dimensionality reduction yields faster retrieval with better accuracy.

## Abstract

Remote Sensing Image Retrieval remains a challenging topic due to the special nature of Remote Sensing Imagery. Such images contain various different semantic objects, which clearly complicates the retrieval task. In this paper, we present an image retrieval pipeline that uses attentive, local convolutional features and aggregates them using the Vector of Locally Aggregated Descriptors (VLAD) to produce a global descriptor. We study various system parameters such as the multiplicative and additive attention mechanisms and descriptor dimensionality. We propose a query expansion method that requires no external inputs. Experiments demonstrate that even without training, the local convolutional features and global representation outperform other systems. After system tuning, we can achieve state-of-the-art or competitive results. Furthermore, we observe that our query expansion method increases overall system performance by about 3%, using only the top-three retrieved images. Finally, we show how dimensionality reduction produces compact descriptors with increased retrieval performance and fast retrieval computation times, e.g. 50% faster than the current systems.