DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing
The effectiveness of hashing methods in big data retrieval has been proved due to their merit in computational and storage efficiency. Recently, encouraged by the strong discriminant capability of deep learning in image representation, various deep hashing methodologies have emerged to enhance retri...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/1/90 |
| _version_ | 1827384477518659584 |
|---|---|
| author | Haiyan Huang Qimin Cheng Zhenfeng Shao Xiao Huang Liyuan Shao |
| author_facet | Haiyan Huang Qimin Cheng Zhenfeng Shao Xiao Huang Liyuan Shao |
| author_sort | Haiyan Huang |
| collection | DOAJ |
| description | The effectiveness of hashing methods in big data retrieval has been proved due to their merit in computational and storage efficiency. Recently, encouraged by the strong discriminant capability of deep learning in image representation, various deep hashing methodologies have emerged to enhance retrieval performance. However, maintaining the semantic richness inherent in remote sensing images (RSIs), characterized by their scene intricacy and category diversity, remains a significant challenge. In response to this challenge, we propose a novel two-stage deep metric and category-level semantic hashing network termed DMCH. First, it introduces a novel triple-selection strategy during the semantic metric learning process to optimize the utilization of triple-label information. Moreover, it inserts a hidden layer to enhance the latent correlation between similar hash codes via a designed category-level classification loss. In addition, it employs additional constraints to keep bit-uncorrelation and bit-balance of generated hash codes. Furthermore, a progressive coarse-to-fine hash code sorting scheme is used for superior fine-grained retrieval and more effective hash function learning. Experiment results on three datasets illustrate the effectiveness and superiority of the proposed method. |
| first_indexed | 2024-03-08T14:58:23Z |
| format | Article |
| id | doaj.art-640740daa26040bcb952308412a16fae |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T14:58:23Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-640740daa26040bcb952308412a16fae2024-01-10T15:07:22ZengMDPI AGRemote Sensing2072-42922023-12-011619010.3390/rs16010090DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote SensingHaiyan Huang0Qimin Cheng1Zhenfeng Shao2Xiao Huang3Liyuan Shao4State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaDepartment of Environmental Sciences, Emory University, Atlanta, GA 30322, USASchool of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, ChinaThe effectiveness of hashing methods in big data retrieval has been proved due to their merit in computational and storage efficiency. Recently, encouraged by the strong discriminant capability of deep learning in image representation, various deep hashing methodologies have emerged to enhance retrieval performance. However, maintaining the semantic richness inherent in remote sensing images (RSIs), characterized by their scene intricacy and category diversity, remains a significant challenge. In response to this challenge, we propose a novel two-stage deep metric and category-level semantic hashing network termed DMCH. First, it introduces a novel triple-selection strategy during the semantic metric learning process to optimize the utilization of triple-label information. Moreover, it inserts a hidden layer to enhance the latent correlation between similar hash codes via a designed category-level classification loss. In addition, it employs additional constraints to keep bit-uncorrelation and bit-balance of generated hash codes. Furthermore, a progressive coarse-to-fine hash code sorting scheme is used for superior fine-grained retrieval and more effective hash function learning. Experiment results on three datasets illustrate the effectiveness and superiority of the proposed method.https://www.mdpi.com/2072-4292/16/1/90deep hash learningcategory-level semanticsremote sensing image retrieval |
| spellingShingle | Haiyan Huang Qimin Cheng Zhenfeng Shao Xiao Huang Liyuan Shao DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing Remote Sensing deep hash learning category-level semantics remote sensing image retrieval |
| title | DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing |
| title_full | DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing |
| title_fullStr | DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing |
| title_full_unstemmed | DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing |
| title_short | DMCH: A Deep Metric and Category-Level Semantic Hashing Network for Retrieval in Remote Sensing |
| title_sort | dmch a deep metric and category level semantic hashing network for retrieval in remote sensing |
| topic | deep hash learning category-level semantics remote sensing image retrieval |
| url | https://www.mdpi.com/2072-4292/16/1/90 |
| work_keys_str_mv | AT haiyanhuang dmchadeepmetricandcategorylevelsemantichashingnetworkforretrievalinremotesensing AT qimincheng dmchadeepmetricandcategorylevelsemantichashingnetworkforretrievalinremotesensing AT zhenfengshao dmchadeepmetricandcategorylevelsemantichashingnetworkforretrievalinremotesensing AT xiaohuang dmchadeepmetricandcategorylevelsemantichashingnetworkforretrievalinremotesensing AT liyuanshao dmchadeepmetricandcategorylevelsemantichashingnetworkforretrievalinremotesensing |