Asymmetric Deep Semantic Quantization for Image Retrieval
Due to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning-based techniques, hashing can outperform non-learning-based hashing technique in many applications. However, we argue that the current deep learning...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8730353/ |
| _version_ | 1828964367774777344 |
|---|---|
| author | Zhan Yang Osolo Ian Raymond Wuqing Sun Jun Long |
| author_facet | Zhan Yang Osolo Ian Raymond Wuqing Sun Jun Long |
| author_sort | Zhan Yang |
| collection | DOAJ |
| description | Due to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning-based techniques, hashing can outperform non-learning-based hashing technique in many applications. However, we argue that the current deep learning-based hashing methods ignore some critical problems (e.g., the learned hash codes are not discriminative due to the hashing methods being unable to discover rich semantic information and the training strategy having difficulty optimizing the discrete binary codes). In this paper, we propose a novel image hashing method, termed as asymmetric deep semantic quantization (ADSQ). The ADSQ is implemented using three stream frameworks, which consist of one LabelNet and two ImgNets. The LabelNet leverages the power of three fully-connected layers, which are used to capture rich semantic information between image pairs. For the two ImgNets, they each adopt the same convolutional neural network structure but with different weights (i.e., asymmetric convolutional neural networks). The two ImgNets are used to generate discriminative compact hash codes. Specifically, the function of the LabelNet is to capture rich semantic information that is used to guide the two ImgNets in minimizing the gap between the real-continuous features and the discrete binary codes. Furthermore, the ADSQ can utilize the most critical semantic information to guide the feature learning process and consider the consistency of the common semantic space and Hamming space. The experimental results on three benchmarks (i.e., CIFAR-10, NUS-WIDE, and ImageNet) demonstrate that the proposed ADSQ can outperform current state-of-the-art methods. |
| first_indexed | 2024-12-14T10:48:36Z |
| format | Article |
| id | doaj.art-1e9a94a181ab447c9083107845f3a049 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:48:36Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1e9a94a181ab447c9083107845f3a0492022-12-21T23:05:20ZengIEEEIEEE Access2169-35362019-01-017726847269510.1109/ACCESS.2019.29207128730353Asymmetric Deep Semantic Quantization for Image RetrievalZhan Yang0https://orcid.org/0000-0002-6336-0228Osolo Ian Raymond1https://orcid.org/0000-0001-9891-6161Wuqing Sun2Jun Long3Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province, School of Computer Science and Engineering, Central South University, Changsha, ChinaNetwork Resources Management and Trust Evaluation Key Laboratory of Hunan Province, School of Computer Science and Engineering, Central South University, Changsha, ChinaNetwork Resources Management and Trust Evaluation Key Laboratory of Hunan Province, School of Computer Science and Engineering, Central South University, Changsha, ChinaNetwork Resources Management and Trust Evaluation Key Laboratory of Hunan Province, School of Computer Science and Engineering, Central South University, Changsha, ChinaDue to its fast retrieval and storage efficiency capabilities, hashing has been widely used in nearest neighbor retrieval tasks. By using deep learning-based techniques, hashing can outperform non-learning-based hashing technique in many applications. However, we argue that the current deep learning-based hashing methods ignore some critical problems (e.g., the learned hash codes are not discriminative due to the hashing methods being unable to discover rich semantic information and the training strategy having difficulty optimizing the discrete binary codes). In this paper, we propose a novel image hashing method, termed as asymmetric deep semantic quantization (ADSQ). The ADSQ is implemented using three stream frameworks, which consist of one LabelNet and two ImgNets. The LabelNet leverages the power of three fully-connected layers, which are used to capture rich semantic information between image pairs. For the two ImgNets, they each adopt the same convolutional neural network structure but with different weights (i.e., asymmetric convolutional neural networks). The two ImgNets are used to generate discriminative compact hash codes. Specifically, the function of the LabelNet is to capture rich semantic information that is used to guide the two ImgNets in minimizing the gap between the real-continuous features and the discrete binary codes. Furthermore, the ADSQ can utilize the most critical semantic information to guide the feature learning process and consider the consistency of the common semantic space and Hamming space. The experimental results on three benchmarks (i.e., CIFAR-10, NUS-WIDE, and ImageNet) demonstrate that the proposed ADSQ can outperform current state-of-the-art methods.https://ieeexplore.ieee.org/document/8730353/Image retrievalquantizationdeep supervised hashing |
| spellingShingle | Zhan Yang Osolo Ian Raymond Wuqing Sun Jun Long Asymmetric Deep Semantic Quantization for Image Retrieval IEEE Access Image retrieval quantization deep supervised hashing |
| title | Asymmetric Deep Semantic Quantization for Image Retrieval |
| title_full | Asymmetric Deep Semantic Quantization for Image Retrieval |
| title_fullStr | Asymmetric Deep Semantic Quantization for Image Retrieval |
| title_full_unstemmed | Asymmetric Deep Semantic Quantization for Image Retrieval |
| title_short | Asymmetric Deep Semantic Quantization for Image Retrieval |
| title_sort | asymmetric deep semantic quantization for image retrieval |
| topic | Image retrieval quantization deep supervised hashing |
| url | https://ieeexplore.ieee.org/document/8730353/ |
| work_keys_str_mv | AT zhanyang asymmetricdeepsemanticquantizationforimageretrieval AT osoloianraymond asymmetricdeepsemanticquantizationforimageretrieval AT wuqingsun asymmetricdeepsemanticquantizationforimageretrieval AT junlong asymmetricdeepsemanticquantizationforimageretrieval |