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.”
Background
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
Items 301–341 of 341
Ensemble of Classification and Matching Models with Alpha-Refine for UAV Tracking
Wang, Z., Chen, S., Bo, C., & Wang, D. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_10
Jiang, J., Xu, M., Pan, S., & Zhu, L. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7946-0_23
Novel Elimination Method of Baseline Drift Basedon Improved Least Square Method
Zhang, R., Xu, X., Zhan, Y., & Xu, T.-T. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7946-0_21
Self-citationZhao, X., Tian, L., & Li, C. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_9
Geometry-Aware Network for Table Structure Recognition in Wild
Xu, B., Liu, H., & Liu, N. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_14
A Bilateral Controller for Pharyngeal Swab Test Teleoperation System
Pu, Y., Li, L., Wang, T., & Sun, Z. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7946-0_10
Super-resolution Reconstruction Based on Capsule Generative Adversarial Network
Wu, Z., Yao, H., Yang, H., Jiang, H., Zhang, W., & Yu, J. (2022) · International Journal of Advanced Network Monitoring and Controls · doi:10.2478/ijanmc-2022-0038
“…intelligence methods have been intensely studied in such fields as intelligent cognition technology [1], efficient image retrieval technology [2], blockchain technology [3], communication virtual mobile network resource management [4], machine motion detection analysis [5], fault…”
BackgroundSport training damage prevention based on hybrid image retrieval scheme
Zhang, Y., & Hou, X. (2023) · Preventive Medicine · doi:10.1016/j.ypmed.2023.107618
WITHDRAWN: A Review Of The Latest Research Technologies Related To 3D Point Cloud
Zhang, X. (2023) · Cognitive Robotics · doi:10.1016/j.cogr.2023.09.001
RetractedSelf-Attention based Deep Hash Learning Method for Efficient Image Retrieval
Yin, F. F., Gao, X., Niu, S., Zhao, H. Y., & Feng, G. (2023) · International Conference on Big Data Technologies (ICBDT) · doi:10.1145/3627377.3627440
“Deep fuzzy hashing network (DFHN) [10] combines fuzzy logic techniques with CNN to learn more effective binary codes.”
MethodImage Recoloring for Color Blindness Considering Naturalness and Harmony
Jin, X., Rong, Y., Zou, D., Wu, Z., & Zhang, X. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9109-9_31
Multiscale Transfer Learning Based Fault Diagnosis of Rolling Bearings
Tang, R., Sun, X., Wang, S., & Chen, Z. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9109-9_36
Unsupervised Person Re-identification via Differentiated Color Perception Learning
Chen, F., Liu, H., Tang, J., & Zhang, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9109-9_38
Improved GR-Convnet for Antipodal Robotic Grasping
Shibasaki, K., Hamamoto, K., & Lu, H. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9109-9_19
Self-citationHigh-Performance Computing Web Search System Based on Computer Big Data
Kang, Y., Bei-ping, T., & Hu, X. (2024) · Scalable Computing Practice and Experience · doi:10.12694/scpe.v25i3.2794
Dacnet: Depth-Aware Convolutional Network for Hyperspectral Image ClassificationPreprint
Chen, G., Zhou, L., Li, L., Wang, J., Zhao, W., Pan, X., & Zhang, W. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4871292
Privacy-Preserving Similarity Retrieval over Medical Images
Zhu, D., Feng, D., & Shen, X. (2024) · Wireless networks · doi:10.1007/978-3-031-76922-1_4
A Violent Language Detection Model Based on Short Text
Li, D., Tan, L., Zou, B., & Liu, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_21
Wu, G., Sun, Q.-X., Xu, J., & Zhang, B.-P. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_3
Point Cloud Completion via Trigonometric Encoding and Self-attention Based Feature Fusion
Wu, Y., Peng, W., Yi-dong, Y., Wu, H., Liu, L., Li, Y., & Yang, B. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_10
Self-citationWu, Y., Zhang, T., Liu, L., Hu, R., Yang, Y., Li, Y., & Yang, B. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_9
Self-citationImproved YOLOv8 Modeling for Earth Observation
Zhao, H., Wang, M., Li, K., Yang, K., Li, L., & Gong, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_28
Application of an Improved Residual Attention Neural Network in Mechanical Part Classification
Zhang, T., & Wang, A. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_30
Layered Clothing Detection Based on Improved YOLOV9
Yan, Z., & Gao, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_26
Yu, L. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_29
Real-Time Student Behavior Analysis via YOLOv5 with Coordinate Attention
Ma, S., Chang, H., Yang, X., Chen, Q., & Han, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_16
Zhao, X., Zuo, J., Wu, H., Qi, T., & Liu, N. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_15
Zhao, X., Wang, K., Zhang, P., Liu, N., & Kan, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_17
Prediction of Typhoon Cloud Maps Based on Self Attention Memory Spatiotemporal Model
Ren, Y., Ye, J., Wang, X., Xiao, F., Huang, D., & Liu, R. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_10
Segmentation of Crack Disaster Images Based on Deep Learning Neural Network Method
Wu, G., Wang, L., Tossou, A. I. H. C. F., Hermilda, C. F. I., Liang, Z., & Xu, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2911-4_1
Application of Multimedia Information Retrieval Technology in Woodblock Pictures Promotion
You, Y. (2025) · Journal of Cases on Information Technology · doi:10.4018/jcit.381312
An Efficient Deep Learning Model for Content Based Medical Image Retrieval
S, S. K. J., & Vigila, S. M. C. (2025) · Global Conference in Emerging Technology (GINOTECH) · doi:10.1109/ginotech63460.2025.11076938
“Diagnosis based on medical imaging is a laborious task, with small lesions often escaping detection, potentially compromising patient care [1].”
A Continual Learning Process to Detect Both Previously Learned and Newly Emerging Attack
Park, H., Kim, T., Lee, H., Shin, D., Shin, D., & Park, M. (2025) · Applied Sciences · doi:10.3390/app151810034
A Benchmark for Document Understanding of Large Language Models in the Field of Electric Power
Zhang, J., Li, Z., Zhang, C., & Chen, H. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4828-6_3
Small Object Detection Using DM-YOLOv10 in Complex Scenes
Yang, L., Wang, M., Jia, Y., Li, L., & Li, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4828-6_4
Self-citationPrivacy-Preserving Image Retrieval Based on Threshold Secret Sharing
Upadhyay, R. R., Padhye, S., Singh, S. P., & Kumar, R. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-3671-9_35
Spatial Attention-Driven Feature Alignment for Underwater Video Super-Resolution
Wang, J., Lu, H., Li, Y., & Kamiya, T. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4821-7_29
Self-citationGeneral Diffusion Transformer for Arbitrary Medical Image Translation
Zheng, J., Wang, X., Luo, Y., Wang, Y., Tang, Y., & Wu, D. O. (2026) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2026.3659832 · Cited by 1
“For instance, Lu et al. [42] combined deep hashing networks with fuzzy logic to address image retrieval problems, while Guo et al. [43] developed an adaptive network-based inference system to tackle classification tasks.”
Similarity-Aware Techniques for Deduplication in Large-Scale Remote Sensing Data
Wang, Y., Zhang, G., Wang, J., Qi, H., & Wang, C. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11400813
“To tackle this, Lu et al. [9] proposed the DFHN method, which combines fuzzy logic and deep neural networks to address the aforementioned issues.”
Deep Contrastive Hashing With Proxy Guidance for Multi-Label Micro-Video Retrieval
Li, Y., Chen, R., Sun, H., Zhao, N., Jing, P., & Gao, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3697677
“Inrecentyears,deephashingmethodshaveattracted widespread attention due to their superior ability to integrate feature representation optimization and hash code generation in an end-to-end manner [17], [18], [19], [20], [21].”
Self-citationJebur, T. K., Lloret, J., Peñalver, L., & Hoomod, H. K. (2026) · Ad Hoc Networks · doi:10.1016/j.adhoc.2026.104462
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.