ML p(r)ior | Visual descriptors for content-based retrieval of remote sensing images

Visual descriptors for content-based retrieval of remote sensing images

2016-02-02
1602.00970 | cs.CV
In this paper we present an extensive evaluation of visual descriptors for the content-based retrieval of remote sensing (RS) images. The evaluation includes global hand-crafted, local hand-crafted, and Convolutional Neural Network (CNNs) features coupled with four different Content-Based Image Retrieval schemes. We conducted all the experiments on two publicly available datasets: the 21-class UC Merced Land Use/Land Cover (LandUse) dataset and 19-class High-resolution Satellite Scene dataset (SceneSat). The content of RS images might be quite heterogeneous, ranging from images containing fine grained textures, to coarse grained ones or to images containing objects. It is therefore not obvious in this domain, which descriptor should be employed to describe images having such a variability. Results demonstrate that CNN-based features perform better than both global and and local hand-crafted features whatever is the retrieval scheme adopted. Features extracted from SatResNet-50, a residual CNN suitable fine-tuned on the RS domain, shows much better performance than a residual CNN pre-trained on multimedia scene and object images. Features extracted from NetVLAD, a CNN that considers both CNN and local features, works better than others CNN solutions on those images that contain fine-grained textures and objects.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-11-03

Image descriptors based on activations of Convolutional Neural Networks (CNNs) have become dominant … show more
PDF

Highlights - Most important sentences from the article

2016-12-19

We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred … show more
PDF

Highlights - Most important sentences from the article

2016-04-29

Image representations derived from pre-trained Convolutional Neural Networks (CNNs) have become the … show more
PDF

Highlights - Most important sentences from the article

2014-03-23

Recent results indicate that the generic descriptors extracted from the convolutional neural network… show more
PDF

Highlights - Most important sentences from the article

2016-04-08

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision ta… show more
PDF

Highlights - Most important sentences from the article

2016-04-05

We propose a novel approach for instance-level image retrieval. It produces a global and compact fix… show more
PDF

Highlights - Most important sentences from the article

2015-11-18

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provi… show more
PDF

Highlights - Most important sentences from the article

2016-10-25

While deep learning has become a key ingredient in the top performing methods for many computer visi… show more
PDF

Highlights - Most important sentences from the article

2015-10-26
1510.07493 | cs.CV

Several recent works have shown that image descriptors produced by deep convolutional neural network… show more
PDF

Highlights - Most important sentences from the article

2015-11-23

We tackle the problem of large scale visual place recognition, where the task is to quickly and accu… show more
PDF

Highlights - Most important sentences from the article

2018-03-29

In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k … show more
PDF

Highlights - Most important sentences from the article

2018-06-22
1806.08565 | cs.CV

The landmark recognition problem is far from being solved, but with the use of features extracted fr… show more
PDF

Highlights - Most important sentences from the article

2019-02-14

MultiGrain is a network architecture producing compact vector representations that are suited both f… show more
PDF

Highlights - Most important sentences from the article

2014-04-07

It has been shown that the activations invoked by an image within the top layers of a large convolut… show more
PDF

Highlights - Most important sentences from the article

2018-05-22

Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance i… show more
PDF

Highlights - Most important sentences from the article

2019-03-03
1903.00905 | cs.CV

Multi-scale deep CNN architecture [1, 2, 3] successfully captures both fine and coarse level image d… show more
PDF