A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval
With the advent of the era of big data, the storage and retrieval of data have become a research hotspot. Hashing methods that transform high-dimensional data into compact binary codes have received increasing attention. Recently, with the successful application of convolutional neural networks in c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8974217/ |
| _version_ | 1818646391625351168 |
|---|---|
| author | Han Sun Yejia Fan Jiaquan Shen Ningzhong Liu Dong Liang Huiyu Zhou |
| author_facet | Han Sun Yejia Fan Jiaquan Shen Ningzhong Liu Dong Liang Huiyu Zhou |
| author_sort | Han Sun |
| collection | DOAJ |
| description | With the advent of the era of big data, the storage and retrieval of data have become a research hotspot. Hashing methods that transform high-dimensional data into compact binary codes have received increasing attention. Recently, with the successful application of convolutional neural networks in computer vision, deep hashing methods utilize an end-to-end framework to learn feature representations and hash codes mutually, which achieve better retrieval performance than conventional hashing methods. However, deep hashing methods still face some challenges in image retrieval. Firstly, most existing deep hashing methods preserve similarity between original data space and hash coding space using loss functions with high time complexity, which cannot get a win-win situation in time and accuracy. Secondly, few existing deep hashing methods are designed for fine-grained image retrieval, which is necessary in practice. In this study, we propose a novel semantics-preserving hashing method which solves the above problems. We add a hash layer before the classification layer as a feature switch layer to guide the classification. At the same time, we replace the complicated loss with the simple classification loss, combining with quantization loss and bit balance loss to generate high-quality hash codes. Besides, we incorporate feature extractor designed for fine-grained image classification into our network for better representation learning. The results on three widely-used fine-grained image datasets show that our method is superior to other state-of-the-art image retrieval methods. |
| first_indexed | 2024-12-17T00:45:54Z |
| format | Article |
| id | doaj.art-1b69280884cc4c8980ae812011140714 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T00:45:54Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1b69280884cc4c8980ae8120111407142022-12-21T22:09:54ZengIEEEIEEE Access2169-35362020-01-018261992620910.1109/ACCESS.2020.29702238974217A Novel Semantics-Preserving Hashing for Fine-Grained Image RetrievalHan Sun0https://orcid.org/0000-0002-2208-6672Yejia Fan1Jiaquan Shen2Ningzhong Liu3Dong Liang4Huiyu Zhou5College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaDepartment of Informatics, University of Leicester, Leicester, U.K.With the advent of the era of big data, the storage and retrieval of data have become a research hotspot. Hashing methods that transform high-dimensional data into compact binary codes have received increasing attention. Recently, with the successful application of convolutional neural networks in computer vision, deep hashing methods utilize an end-to-end framework to learn feature representations and hash codes mutually, which achieve better retrieval performance than conventional hashing methods. However, deep hashing methods still face some challenges in image retrieval. Firstly, most existing deep hashing methods preserve similarity between original data space and hash coding space using loss functions with high time complexity, which cannot get a win-win situation in time and accuracy. Secondly, few existing deep hashing methods are designed for fine-grained image retrieval, which is necessary in practice. In this study, we propose a novel semantics-preserving hashing method which solves the above problems. We add a hash layer before the classification layer as a feature switch layer to guide the classification. At the same time, we replace the complicated loss with the simple classification loss, combining with quantization loss and bit balance loss to generate high-quality hash codes. Besides, we incorporate feature extractor designed for fine-grained image classification into our network for better representation learning. The results on three widely-used fine-grained image datasets show that our method is superior to other state-of-the-art image retrieval methods.https://ieeexplore.ieee.org/document/8974217/Deep hashingfine-grained imagesfeature switch layerimage retrieval |
| spellingShingle | Han Sun Yejia Fan Jiaquan Shen Ningzhong Liu Dong Liang Huiyu Zhou A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval IEEE Access Deep hashing fine-grained images feature switch layer image retrieval |
| title | A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval |
| title_full | A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval |
| title_fullStr | A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval |
| title_full_unstemmed | A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval |
| title_short | A Novel Semantics-Preserving Hashing for Fine-Grained Image Retrieval |
| title_sort | novel semantics preserving hashing for fine grained image retrieval |
| topic | Deep hashing fine-grained images feature switch layer image retrieval |
| url | https://ieeexplore.ieee.org/document/8974217/ |
| work_keys_str_mv | AT hansun anovelsemanticspreservinghashingforfinegrainedimageretrieval AT yejiafan anovelsemanticspreservinghashingforfinegrainedimageretrieval AT jiaquanshen anovelsemanticspreservinghashingforfinegrainedimageretrieval AT ningzhongliu anovelsemanticspreservinghashingforfinegrainedimageretrieval AT dongliang anovelsemanticspreservinghashingforfinegrainedimageretrieval AT huiyuzhou anovelsemanticspreservinghashingforfinegrainedimageretrieval AT hansun novelsemanticspreservinghashingforfinegrainedimageretrieval AT yejiafan novelsemanticspreservinghashingforfinegrainedimageretrieval AT jiaquanshen novelsemanticspreservinghashingforfinegrainedimageretrieval AT ningzhongliu novelsemanticspreservinghashingforfinegrainedimageretrieval AT dongliang novelsemanticspreservinghashingforfinegrainedimageretrieval AT huiyuzhou novelsemanticspreservinghashingforfinegrainedimageretrieval |