Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling
<b> </b>As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/17/2789 |
id |
doaj-61face4067854635bba345454f446069 |
---|---|
record_format |
Article |
spelling |
doaj-61face4067854635bba345454f4460692020-11-25T03:54:54ZengMDPI AGRemote Sensing2072-42922020-08-01122789278910.3390/rs12172789Deep Hash Remote Sensing Image Retrieval with Hard Probability SamplingXue Shan0Pingping Liu1Guixia Gou2Qiuzhan Zhou3Zhen Wang4College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Communication Engineering, Jilin University, Changchun 130012, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China<b> </b>As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows the retrieval time and takes up a great deal of memory space. The hash method is being increasingly used for rapid image retrieval because of its remarkably fast performance. At the same time, selecting samples that contain more information and greater stability to train the network has gradually become the key to improving retrieval performance. Given the above considerations, we propose a deep hash remote sensing image retrieval method, called the hard probability sampling hash retrieval method (HPSH), which combines hash code learning with hard probability sampling in a deep network. Specifically, we used a probability sampling method to select training samples, and we designed one novel hash loss function to better train the network parameters and reduce the hashing accuracy loss due to quantization. Our experimental results demonstrate that HPSH could yield an excellent representation compared with other state-of-the-art hash approaches. For the university of California, merced (UCMD) dataset, HPSH+S resulted in a mean average precision (mAP) of up to 90.9% on 16 hash bits, 92.2% on 24 hash bits, and 92.8% on 32 hash bits. For the aerial image dataset (AID), HPSH+S achieved a mAP of up to 89.8% on 16 hash bits, 93.6% on 24 hash bits, and 95.5% on 32 hash bits. For the UCMD dataset, with the use of data augmentation, our proposed approach achieved a mAP of up to 99.6% on 32 hash bits and 99.7% on 64 hash bits.https://www.mdpi.com/2072-4292/12/17/2789hashremote sensing image retrievalsemantic similarityquantization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xue Shan Pingping Liu Guixia Gou Qiuzhan Zhou Zhen Wang |
spellingShingle |
Xue Shan Pingping Liu Guixia Gou Qiuzhan Zhou Zhen Wang Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling Remote Sensing hash remote sensing image retrieval semantic similarity quantization |
author_facet |
Xue Shan Pingping Liu Guixia Gou Qiuzhan Zhou Zhen Wang |
author_sort |
Xue Shan |
title |
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling |
title_short |
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling |
title_full |
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling |
title_fullStr |
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling |
title_full_unstemmed |
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling |
title_sort |
deep hash remote sensing image retrieval with hard probability sampling |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-08-01 |
description |
<b> </b>As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows the retrieval time and takes up a great deal of memory space. The hash method is being increasingly used for rapid image retrieval because of its remarkably fast performance. At the same time, selecting samples that contain more information and greater stability to train the network has gradually become the key to improving retrieval performance. Given the above considerations, we propose a deep hash remote sensing image retrieval method, called the hard probability sampling hash retrieval method (HPSH), which combines hash code learning with hard probability sampling in a deep network. Specifically, we used a probability sampling method to select training samples, and we designed one novel hash loss function to better train the network parameters and reduce the hashing accuracy loss due to quantization. Our experimental results demonstrate that HPSH could yield an excellent representation compared with other state-of-the-art hash approaches. For the university of California, merced (UCMD) dataset, HPSH+S resulted in a mean average precision (mAP) of up to 90.9% on 16 hash bits, 92.2% on 24 hash bits, and 92.8% on 32 hash bits. For the aerial image dataset (AID), HPSH+S achieved a mAP of up to 89.8% on 16 hash bits, 93.6% on 24 hash bits, and 95.5% on 32 hash bits. For the UCMD dataset, with the use of data augmentation, our proposed approach achieved a mAP of up to 99.6% on 32 hash bits and 99.7% on 64 hash bits. |
topic |
hash remote sensing image retrieval semantic similarity quantization |
url |
https://www.mdpi.com/2072-4292/12/17/2789 |
work_keys_str_mv |
AT xueshan deephashremotesensingimageretrievalwithhardprobabilitysampling AT pingpingliu deephashremotesensingimageretrievalwithhardprobabilitysampling AT guixiagou deephashremotesensingimageretrievalwithhardprobabilitysampling AT qiuzhanzhou deephashremotesensingimageretrievalwithhardprobabilitysampling AT zhenwang deephashremotesensingimageretrievalwithhardprobabilitysampling |
_version_ |
1724471922651037696 |