Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval

TL;DR

This paper introduces a multi-label remote sensing image retrieval method using fully convolutional networks to better handle complex images with multiple classes, achieving state-of-the-art results.

Contribution

It proposes a novel multi-label RSIR approach with FCN that predicts segmentation maps and extracts region features for improved retrieval performance.

Findings

Achieves state-of-the-art retrieval accuracy

Outperforms conventional single-label methods

Effective in handling complex multi-label images

Abstract

Conventional remote sensing image retrieval (RSIR) systems usually perform single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. This assumption, however, ignores the complexity of remote sensing images, where an image might have multiple classes (i.e., multiple labels), thus resulting in worse retrieval performance. We therefore propose a novel multi-label RSIR approach with fully convolutional networks (FCN). In our approach, we first train a FCN model using a pixel-wise labeled dataset,and the trained FCN is then used to predict the segmentation maps of each image in the considered archive. We finally extract region convolutional features of each image based on its segmentation map.The region features can be either used to perform region-based retrieval or further post-processed to obtain a feature vector for similarity measure. The experimental results show that our approach achieves state-of-the-art performance in contrast to conventional single-label and recent multi-label RSIR approaches.