Deep Fuzzy Hashing Network for Efficient Image Retrieval
The DOI matches its Crossref record; 61 of the 64 references it cites were found in a registry or an index.
Abstract
Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming space with similarity well preserved. The traditional hashing methods usually represent image content by hand-crafted features. Deep hashing methods based on deep neural network (DNN) architectures can generate more effective image features and obtain better retrieval performance. However, the underlying data structure is hardly captured by existing DNN models. Moreover, the similarity (either visually or semantically) between pairwise images is ambiguous, even uncertain, to be measured in the existing deep hashing methods. In this article, we propose a novel hashing method termed deep fuzzy hashing network (DFHN) to overcome the shortcomings of existing deep hashing approaches. Our DFHN method combines the fuzzy logic technique and the DNN to learn more effective binary codes, which can leverage fuzzy rules to model the uncertainties underlying the data. Derived from fuzzy logic theory, the generalized hamming distance is devised in the convolutional layers and fully connected layers in our DFHN to model their outputs, which come from an efficientxoroperation on given inputs and weights. Extensive experiments show that our DFHN method obtains competitive retrieval accuracy with highly efficient training speed compared with several state-of-the-art deep hashing approaches on two large-scale image datasets: CIFAR-10 and NUS-WIDE.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Inspired by the powerful capability on visual representation [10], [35], [36], some deep hashing methods have been proposed [5], [20], [23], [24] to learn more effective hash codes by taking advantage of sophisticated DNNs.”
BackgroundMethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“Inspired by the powerful capability on visual representation [10], [35], [36], some deep hashing methods have been proposed [5], [20], [23], [24] to learn more effective hash codes by taking advantage of sophisticated DNNs.”
BackgroundMethodU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“The major innovations in the CNN have been proposed since the remarkable classification performance achieved by AlexNet [10] trained on the large-scale ImageNet dataset [34].”
MethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 2×
“Earlierworkcommonlyutilizes hand-crafted real-valued features [1], [2], [7]–[9] for image representations and rank the images in the database regarding their distances (e.g., Euclidian or cosine distance) to the query image in the feature space.”
BackgroundDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“, image classification [13], [14], object detection [15], image segmentation [16], image-text matching [17], etc.”
BackgroundSURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · cited 1×
“Earlier work commonly utilizes hand-crafted real-valued features [1], [2], [7]–[9] for image representations and rank the images in the database regarding their”
MethodContent-based image retrieval at the end of the early years
Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A., & Jain, R. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.895972 · Cited by 6,056
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
(1999) · Cited by 3,186
A survey of the recent architectures of deep convolutional neural networks
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09825-6 · Cited by 3,137 · cited 1×
“The comprehensive survey on DNNs can be found in [32].”
BackgroundNUS-WIDE: a real-world web image database from National University of Singapore
Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009) · Proceedings of the ACM International Conference on Image and Video Retrieval · doi:10.1145/1646396.1646452 · Cited by 3,025 · cited 1×
“In this section, we first describe the experimental configu-ration on two benchmark image datasets (CIFAR-10 [58] and NUS-WIDE [59]).”
MethodWeiss, Y., Torralba, A. B., & Fergus, R. (2008) · neural information processing systems · Cited by 2,767
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153 · cited 1×
“A typical CNN model consists of several stacked structures of the convolutional layer, the nonlinear activation unit, the subsampling layer, and the fully connected layer [33], which jointly model the complex nonlinearity of the observed data.”
BackgroundGong, Y., Lazebnik, S., Gordo, A., & Perronnin, F. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.193 · Cited by 1,834 · cited 11×
“ing unsupervised methods LSH [18], SH [49], ITQ [7], and CCA-ITQ [7] and supervised methods MLH [20], BRE [60], KSH [19], CNHN [25], and DLBHC [22].”
BackgroundMethodInfluentialDeep Neural Networks for Object Detection
Szegedy, C., Toshev, A., & Erhan, D. (2013) · neural information processing systems · Cited by 1,662
Neural-network-based fuzzy logic control and decision system
Lin, C.-T., & Lee, C. S. G. (1991) · IEEE Transactions on Computers · doi:10.1109/12.106218 · Cited by 1,480 · cited 1×
“In this article, we consider utilizing the fuzzy logic techniques [29], [30] to tackle the aforementioned limitations of existing deep hashing methods.”
MethodSupervised hashing with kernels
Liu, W., Wang, J., Ji, R., Jiang, Y.-G., & Chang, S.-F. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247912 · Cited by 1,351 · cited 3×
“For example, the typical method of supervised hashing with kernels (KSH) [19] learns hash functions by modeling the pairwise similarities between data samples according to labels.”
MethodNeural Codes for Image Retrieval
Babenko, A., Slesarev, A., Chigorin, A., & Lempitsky, V. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_38 · Cited by 1,192
Supervised Hashing for Image Retrieval via Image Representation Learning
Xia, R., Pan, Y., Lai, H., Liu, C., & Yan, S. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8952 · Cited by 952 · cited 4×
“The earlier work of CNNH [25] adopts a two-stage framework that learns hash codes and image representations in two successive steps.”
MethodInfluentialDeep Supervised Hashing for Fast Image Retrieval
Liu, H., Wang, R., Shan, S., & Chen, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.227 · Cited by 933
Simultaneous feature learning and hash coding with deep neural networks
Lai, H., Pan, Y., Liu, Y., & Yan, S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298947 · Cited by 884 · cited 3×
“To tackle the limitation of the two-stage learning scheme, the later methods, such as network in network hashing [26] and ranking-based hashing approaches [27], [28], have been proposed to simultaneously conduct feature learning and hashing code learning.”
MethodSemi-Supervised Hashing for Large-Scale Search
Wang, J., Kumar, S., & Chang, S.-F. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.48 · Cited by 810 · cited 1×
“For example, the SSH method [55] takes the labeled data samples to extract pairwise information for preserving the semantic similarity; the semisupervised discriminant hashing approach [56] utilizes the labeled data to maximize the separability of image samples from different classes.”
MethodLearning to Hash with Binary Reconstructive Embeddings
Kulis, B., & Darrell, T. (2009) · Cited by 806
Minimal Loss Hashing for Compact Binary Codes
Norouzi, M., & Blei, D. M. (2011) · International Conference on Machine Learning · Cited by 765
Deep Hashing Network for Efficient Similarity Retrieval
Zhu, H., Long, M., Wang, J., & Cao, Y. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10235 · Cited by 664 · cited 1×
“Later in [26], [27], and [57], an end-to-end one-stage pipeline is developed to perform simultaneous feature learning and hash encoding, which generally obtains more compact hash codes than the two-stage CNNH method.”
MethodDeep learning of binary hash codes for fast image retrieval
Lin, K., Yang, H.-F., Hsiao, J.-H., & Chen, C.-S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301269 · Cited by 614 · cited 3×
“9) DLBHC [22]: DLBHC employs a hidden layer of the CNN to learn binary coding that can represent the potential semantics of image category labels in a pointwise way.”
MethodDeep semantic ranking based hashing for multi-label image retrieval
Zhao, F., Huang, Y., Wang, L., & Tan, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298763 · Cited by 564 · cited 2×
“To tackle the limitation of the two-stage learning scheme, the later methods, such as network in network hashing [26] and ranking-based hashing approaches [27], [28], have been proposed to simultaneously conduct feature learning and hashing code learning.”
MethodMathematics of Fuzzy Sets and Fuzzy Logic
Bede, B. (2013) · Studies in Fuzziness and Soft Computing · doi:10.1007/978-3-642-35221-8 · Cited by 540 · cited 1×
“The concept of the FNN [39] is invented in the early 1990s with the combination of fuzzy logic and the neural network, to enhance the neural networks with the interpretability of fuzzy logic [40], [41].”
MethodLearning Discriminative Binary Codes for Large-scale Cross-modal Retrieval
Xu, X., Shen, F., Yang, Y., Shen, H. T., & Li, X. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2676345 · Cited by 458 · cited 1×
“Whenthelabelinformationofdataisavail-able,thesupervisedhashingmethods[52]–[54]areproposed toleveragethelabelsassemanticinformationtogeneratemore effective hash codes.”
Self-citationZhang, R., Lin, L., Zhang, R., Zuo, W., & Zhang, L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2467315 · Cited by 448
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization
Shen, F., Xu, Y., Liu, L., Yang, Y., Huang, Z., & Shen, H. T. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2789887 · Cited by 407
Self-citationA Hierarchical Fused Fuzzy Deep Neural Network for Data Classification
Deng, Y., Ren, Z., Kong, Y., Bao, F., & Dai, Q. (2017) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2016.2574915 · Cited by 396
Cross-Modal Attention With Semantic Consistence for Image–Text Matching
Xu, X., Wang, T., Yang, Y., Zuo, L., Shen, F., & Shen, H. T. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2967597 · Cited by 279 · cited 1×
“, image classification [13], [14], object detection [15], image segmentation [16], image-text matching [17], etc.”
BackgroundSelf-citationOn the principles of fuzzy neural networks
Gupta, M. M., & Rao, D. H. (1994) · Fuzzy Sets and Systems · doi:10.1016/0165-0114(94)90279-8 · Cited by 264
Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive
Lin, F.-J., Lin, C.-H., & Shen, P.-H. (2001) · IEEE Transactions on Fuzzy Systems · doi:10.1109/91.963761 · Cited by 250 · cited 1×
“The FNN inherits the merit of fuzzy logic that can overcome the uncertainties underlying the observed data, and it has proved to be useful for various practical problems, e.g., image processing [42], [43], control system [44], [45], data encryption [46], etc.”
BackgroundA fuzzy neural network and its application to pattern recognition
Kwan, H. K., & Cai, Y. (1994) · IEEE Transactions on Fuzzy Systems · doi:10.1109/91.298447 · Cited by 240 · cited 1×
“The FNN inherits the merit of fuzzy logic that can overcome the uncertainties underlying the observed data, and it has proved to be useful for various practical problems, e.g., image processing [42], [43], control system [44], [45], data encryption [46], etc.”
BackgroundExploiting Subspace Relation in Semantic Labels for Cross-Modal Hashing
Shen, H. T., Liu, L., Yang, Y., Xu, X., Huang, Z., Shen, F., & Hong, R. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2970050 · Cited by 230 · cited 1×
“To overcome the inefficiency of real-valued image features for CBIR, recent hashing approaches [18]–[21] have received broadattention,sincetheycansignificantlyspeeduptheretrieval process when dealing with a large-scale dataset.”
Self-citationTernary Adversarial Networks With Self-Supervision for Zero-Shot Cross-Modal Retrieval
Xu, X., Lu, H., Song, J., Yang, Y., Shen, H. T., & Li, X. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2928180 · Cited by 205 · cited 1×
“In the past decade, the problem of content-based image retrieval (CBIR) [1]–[4] has become a research hotspot, which aims at searching for similar images given a query image accordingtotheirvisualcontents,where“similar”mayrepresent “visualsimilar”or“semanticsimilar”[5].”
BackgroundSelf-citationA Fast Optimization Method for General Binary Code Learning
Shen, F., Zhou, X., Yang, Y., Song, J., Shen, H. T., & Tao, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2612883 · Cited by 159
Self-citationSSDH: Semi-Supervised Deep Hashing for Large Scale Image Retrieval
Zhang, J., & Peng, Y. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2771332 · Cited by 156 · cited 3×
“For example, the SSH method [55] takes the labeled data samples to extract pairwise information for preserving the semantic similarity; the semisupervised discriminant hashing approach [56] utilizes the labeled data to maximize the separability of image samples from different classes.”
MethodGraph Convolutional Network Hashing
Zhou, X., Shen, F., Liu, L., Liu, W., Nie, L., Yang, Y., & Shen, H. T. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2883970 · Cited by 143 · cited 1×
“Inspired by the powerful capability on visual representation [10], [35], [36], some deep hashing methods have been proposed [5], [20], [23], [24] to learn more effective hash codes by taking advantage of sophisticated DNNs.”
MethodSelf-citationIndexing chromatic and achromatic patterns for content-based colour image retrieval
Qiu, G. (2002) · Pattern Recognition · doi:10.1016/s0031-3203(01)00162-5 · Cited by 138
Liu, X., He, J., Deng, C. D., & Lang, B. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.275 · Cited by 131
Hashing on Nonlinear Manifolds
Shen, F., Shen, C., Shi, Q., van den Hengel, A., Tang, Z., & Shen, H. T. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2405340 · Cited by 130 · cited 1×
“Compared to the L 2 -norm widely used in several existing hashing methods [7], [20], [53], the L 1 -norm has lower efficiency and its output is sparse, which means some unimportant features will be set to zero directly; therefore, the subgradients it produces may ignore the information buried in…”
MethodSelf-citationRobust discrete code modeling for supervised hashing
Luo, Y., Yang, Y., Shen, F., Huang, Z. H., Zhou, P., & Shen, H. T. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.02.034 · Cited by 117 · cited 2×
“distributions, several data-dependent approaches [49]–[52] are further developed.”
BackgroundMethodSelf-citationPezeshki, Z., & Mazinani, S. M. (2018) · Artificial Intelligence Review · doi:10.1007/s10462-018-9630-6 · Cited by 114 · cited 2×
“niques [29], [30] to tackle the aforementioned limitations of existing deep hashing methods.”
BackgroundHashing with Mutual Information
Cakir, F., He, K., Bargal, S. A., & Sclaroff, S. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2914897 · Cited by 100 · cited 2×
“Inspired from the recent advancement of DNNs, several deep hashing approaches [5], [20], [22]–[24] have been developed to take advantage of the superior feature representation capability of DNNs.”
MethodAn Interval Type-2 Neural Fuzzy System for Online System Identification and Feature Elimination
Lin, C., Pal, N. R., Wu, S.-L., Liu, Y., & Lin, Y.-Y. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2346537 · Cited by 86 · cited 1×
“The FNN inherits the merit of fuzzy logic that can overcome the uncertainties underlying the observed data, and it has proved to be useful for various practical problems, e.g., image processing [42], [43], control system [44], [45], data encryption [46], etc.”
BackgroundComplex Fuzzy Sets and Complex Fuzzy Logic an Overview of Theory and Applications
Tamir, D. E., Rishe, N. D., & Kandel, A. (2015) · Studies in fuzziness and soft computing · doi:10.1007/978-3-319-19683-1_31 · Cited by 81 · cited 1×
“enhance the neural networks with the interpretability of fuzzy logic [40], [41].”
BackgroundLearning unified binary codes for cross-modal retrieval via latent semantic hashing
Xu, X., He, L., Shimada, A., Taniguchi, R.-I., & Lu, H. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.11.133 · Cited by 52 · cited 1×
“Earlierworkcommonlyutilizes hand-crafted real-valued features [1], [2], [7]–[9] for image representations and rank the images in the database regarding their distances (e.g., Euclidian or cosine distance) to the query image in the feature space.”
BackgroundSelf-citationDeep Neural Networks for Object Detection
You, J. (2022) · Highlights in Science, Engineering and Technology · doi:10.54097/hset.v17i.2576 · Cited by 46
Xor-Implications and E-Implications: Classes of Fuzzy Implications Based on Fuzzy Xor
Bedregal, B., Reiser, R., & Dimuro, G. P. (2009) · Electronic Notes in Theoretical Computer Science · doi:10.1016/j.entcs.2009.07.045 · Cited by 44 · cited 1×
“The FNN is limitedly investigated and applied on some toy examples, such as [47] and [48].”
MethodComplex Fuzzy Sets and Complex Fuzzy Logic. An Overview of Theory and Applications
(2018) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789813238183_0011 · Cited by 36
Fuzzy implications and inference processes
Tick, J., & Fodor, J. C. (2006) · IEEE International Conference on Computational Cybernetics (ICCC) · doi:10.1109/icccyb.2005.1511558 · Cited by 29 · cited 1×
“The FNN is limitedly investigated and applied on some toy examples, such as [47] and [48].”
MethodTwo-stage data encryption using chaotic neural networks
Srivastava, G., Kumar, C. N. S. V., Kavitha, V., Parthiban, N., & Venkataraman, R. (2012) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-179543 · Cited by 28 · cited 1×
“The FNN inherits the merit of fuzzy logic that can overcome the uncertainties underlying the observed data, and it has proved to be useful for various practical problems, e.g., image processing [42], [43], control system [44], [45], data encryption [46], etc.”
BackgroundFan, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10328 · Cited by 16 · cited 2×
“Recently, Fan [31] has revisited the FNN and explored the useful technique of a generalized hamming distance in it to improve the effectiveness and efficiency of the neural network training procedure.”
BackgroundMethod
Research works printed but not linked: 1
- krizhevsky, 0, ImagNet classification with deep convolutional neural networks, Proc Annu Conf Neural Inf Process Syst, 1106
Cited by
Substantial capabilities of robotics in enhancing industry 4.0 implementation
Javaid, M., Haleem, A., Singh, R. P., & Suman, R. (2021) · Cognitive Robotics · doi:10.1016/j.cogr.2021.06.001 · Cited by 563
Liu, Y., Garg, S., Nie, J., Zhang, Y., Xiong, Z., Kang, J., & Hossain, M. S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3011726 · Cited by 541
“[14] proposed a long short-term memory (LSTM) networks-based deep learning model to achieve anomaly detection in sensing time-series”
BackgroundLiang, S., Wu, H., Zhen, L., Hua, Q., Garg, S., Kaddoum, G., Hassan, M. M., & Yu, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3158253 · Cited by 367
“However, massive amounts of data will be generated in this scenario, especially image and video, which are transmitted to the edge layer of the network [5], [6].”
BackgroundKumar, S., Yadav, D., Gupta, H., Verma, O. P., Ansari, I. A., & Ahn, C. W. (2020) · Electronics · doi:10.3390/electronics10010014 · Cited by 165
Freitas de Araujo-Filho, P., Kaddoum, G., Campelo, D. R., Gondim Santos, A., Macedo, D., & Zanchettin, C. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3024800 · Cited by 153
“In [30], a novel hashing method is suggested to overcome existing deep hashing approaches challenges.”
Method
Metadata
- Authors
- Lu, H., Zhang, M., Xu, X., Li, Y., & Shen, H. T.
- Affiliations
- Kyushu Institute of Technology (JP)
- University of Electronic Science and Technology of China (CN)
- Venue
- IEEE Transactions on Fuzzy Systems
- Published
- 2021-01
- Volume
- 29
- Issue
- 1
- Pages
- 166-176
- ISSN
- 1063-6706 (ISSN-L)
- 1941-0034
- OpenAlex
- W3014847672
- Cited by
- 340
- References
- 64
- Citations by year
- 2026: 9 · 2025: 31 · 2024: 52 · 2023: 38 · 2022: 139 · 2021: 63
- FWCI
- 24.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Fuzzy Systems (publishedVersion)
- Funders
- National Key Research and Development Program of China (2018AAA0102200)
- National Natural Science Foundation of China (61976049, 61632007)
- Leading Initiative for Excellent Young Researchers of Ministry of Education, Culture, Sports, Science and Technology, Japan (16809746)
- Sichuan Science and Technology Program, China (2019ZDZX0008, 2018GZDZX0032)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- deep hashing, image retrieval, fuzzy logic, binary codes, Hamming space, fuzzy rules, uncertainty modeling, convolutional layers, XOR operation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.