Cited by 936Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval Techniques

The DOI matches its Crossref record; 37 of the 44 references it cites were found in a registry or an index.

HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition

Yan, Zhicheng, Zhang, Hao, Piramuthu, Robinson, Jagadeesh, Vignesh, DeCoste, Dennis, Di, Wei, Yu, Yizhou·2015·2015 IEEE International Conference on Computer Vision (ICCV)

DOI 10.1109/iccv.2015.314

Open this paper in CoChat — free account

Abstract

In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifiers, and few efforts have been made to leverage the hierarchical structure of categories. In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a two-level category hierarchy. An HD-CNN separates easy classes using a coarse category classifier while distinguishing difficult classes using fine category classifiers. During HDCNN training, component-wise pretraining is followed by global fine-tuning with a multinomial logistic loss regularized by a coarse category consistency term. In addition, conditional executions of fine category classifiers and layer parameter compression make HD-CNNs scalable for largescale visual recognition. We achieve state-of-the-art results on both CIFAR100 and large-scale ImageNet 1000-class benchmark datasets. In our experiments, we build up three different two-level HD-CNNs, and they lower the top-1 error of the standard CNNs by 2:65%, 3:1%, and 1:1%.

Integrity signals

Registry

Crossref · 10.1109/iccv.2015.314

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
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 23,889
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 1×
“Specifically, we choose product quantization [14] to compress the parameter matrix W ∈ Rm×n.”
Method

Flagged first, then by citations

Show all 44 references

7 of the 44 references couldn’t be matched to a known paper.

Research works printed but not linked: 4

jia, 2013, Caffe An Open Source Convolutional Architecture for Fast Feature Embedding
jia, 2013, Visual concept learning: Combining machine vision and bayesian generalization on concept hierarchies, NIPS
lee, 2014, Deeply-supervised nets arXiv preprint arXiv 1409 5185
lin, 2013, Network in network, CoRR

Sorted by citations

Items 401–500 of 929

Speech densely connected convolutional networks for small-footprint keyword spotting
Tsai, T., & Lin, X.-H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14617-5 · Cited by 7
Spectral Segmentation Multi-Scale Feature Extraction Residual Networks for Hyperspectral Image Classification
Wang, J., Ren, J., Peng, Y., & Shi, M. (2023) · Remote Sensing · doi:10.3390/rs15174219 · Cited by 7
3D convolutional long short-term encoder-decoder network for moving object segmentation
Turker, A., & Ekşioğlu, E. M. (2023) · Computer Science and Information Systems · doi:10.2298/csis230129044t · Cited by 7
AFLOW: Developing Adversarial Examples Under Extremely Noise-Limited Settings
Liu, R., Zhang, J., Li, H., Zhang, J., Wang, Y., & Zhou, W. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-7356-9_30 · Cited by 7
Automatic detection of delamination on tunnel lining surfaces from laser 3D point cloud data by 3D features and a support vector machine
Mizutani, T., Yamaguchi, T., Yamamoto, K., Ishida, T., Nagata, Y., Kawamura, H., Tokuno, T., Suzuki, K., & Yamaguchi, Y. (2023) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-023-00731-3 · Cited by 7
AI‐based motion artifact severity estimation in undersampled MRI allowing for selection of appropriate reconstruction models
Beljaards, L., Pezzotti, N., Rao, C., Doneva, M., van Osch, M. J. P., & Staring, M. (2024) · Medical Physics · doi:10.1002/mp.16918 · Cited by 7
Optimum splitting computing for DNN training through next generation smart networks: a multi-tier deep reinforcement learning approach
Lien, S., Yeh, C.-H., & Deng, D. (2024) · Wireless Networks · doi:10.1007/s11276-023-03600-5 · Cited by 7
InaTechShips: A validation study of a novel ship dataset through deep learning-based classification and detection models for maritime applications
Teixeira, E. H., Mafra, S. B., & de Figueiredo, F. A. P. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.120823 · Cited by 7
Not All Pixels are Equal: Learning Pixel Hardness for Semantic Segmentation
Xiao, X., Zhou, D., Hu, J., Hu, Y., & Xu, Y. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02416-4 · Cited by 8
Cervical Lesion Detection Net
Bai, B., Du, Y., Li, P., & Lv, Y. (2019) · IEEE International Conference on Anti-counterfeiting, Security, and Identification (ASID) · doi:10.1109/icasid.2019.8925284 · Cited by 7
“3, the basic CNN model of the feature extraction network draws on the VGG deep learning model[7], and selects the feature maps of the first, third, and fifth convolution layers.”
BackgroundMethodInfluential
Semantic Hierarchy-based Convolutional Neural Networks for Image Classification
Inoue, M. G. S., Forster, C. H. Q., & dos Santos, A. C. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207246 · Cited by 7
“One work that represents the state-of-art of hierarchical CNNs is the HD-CNN (Hierarchical Deep CNNs) proposed by Yan et al [6], that is composed by coarse component networks trained over all classes and ﬁne component networks trained on the hierarchical ﬁne classes.”
Background
Varietal quality control in the nursery plant industry using computer vision and deep learning techniques
Borraz‐Martínez, S., Tarrés, F., Boqué, R., Mestre, M., Simó, J., & Gras, A. (2020) · Journal of Chemometrics · doi:10.1002/cem.3320 · Cited by 7
A Hybrid Classifier for Handwriting Recognition on Multi-domain Financial Bills Based on DCNN and SVM
Wang, S., Yuan, B., & Wu, D. X. (2020) · Traitement du signal · doi:10.18280/ts.370623 · Cited by 7
“The DCNNs with such a structure include AlexNet [8], ZFNet [9], VGGNet [10], GoogLeNet [11], and ResNet [12].”
Method
Forecasting and identifying the meteorological and hydrological conditions favoring the occurrence of severe hazes in Beijing and Shanghai using deep learning
Wang, C. (2021) · Atmospheric chemistry and physics · doi:10.5194/acp-21-13149-2021 · Cited by 7
CF-CNN: Coarse-to-Fine Convolutional Neural Network
Park, J., Kim, H., & Paik, J. (2021) · Applied Sciences · doi:10.3390/app11083722 · Cited by 7
“As a result, classification performance is improved at the cost of additional subnetworks and the corresponding learning method for each class group [19].”
Influential
Building hierarchical class structures for extreme multi-class learning
Huang, H., Wang, Y., & Hu, Q. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01783-z · Cited by 7
“Early works [20, 29, 30] construct hierarchy basing on confusion matrix, minimize the coarse category classification error rate.”
Background
Encoding Hierarchical Information in Neural Networks Helps in Subpopulation Shift
Mukherjee, A., Garg, I., & Roy, K. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3261861 · Cited by 7
“[19]introducedhierarchicaldeep convolutionalneuralnetwork(HD-CNN),whichusesabase classiﬁertodistinguishbetweencoarsercategorieswhereasfor distinguishingbetweenconfusingclasses,thetaskispushed furtherdownstreamtotheﬁnecategoryclassiﬁers.”
ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
Wu, T.-Y., Ho, C.-H., & Vasconcelos, N. M. (2024) · 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/cvpr52733.2024.01564 · Cited by 10
“Several works [1, 13, 18, 24, 41, 47] propose hierarchical classifiers for CNN-based deep models.”
Background
Decoding the Deep: Exploring Class Hierarchies of Deep Representations Using Multiresolution Matrix Factorization
Ithapu, V. K. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.216 · Cited by 7
“The networks are not trained to learn the hierarchy of categories (unlike the alternate works from [33, 7, 2]) – the”
Background
HSD-CNN
SaiRam, K., Mukherjee, J., Patra, A., & Das, P. P. (2018) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3293353.3293383 · Cited by 8
“[20], Grouped Convolutions [21, 22]. Very few attempts have been made to exploit category hierarchies [3–5] in deep CNN models, and they are restricted to two levels. Hierarchical deep CNN’s (HD-CNN) [3] embed deep CNN’s into a two-level category hierarchy. They separate easy classes using a coarse category classifier…”
Influential
Leveraging organizational resources to adapt models to new data modalities
Suri, S., Chanda, R., Bulut, N., Narayana, P., Zeng, Y., Bailis, P. D., Basu, S., Narlikar, G., Ré, C., & Sethi, A. (2020) · Proceedings of the VLDB Endowment · doi:10.14778/3415478.3415559 · Cited by 7
“…feature space, while we focus on the opportunities of weak supervision, we can also consider methods for unsupervised domain adaptation [61], extensions to our initial integration with semi-supervised learning [15], and extensions of universal or semantic embedding construction [26,43,69,73].”
Method
Industrial Fault Detection Using Transfer Learning Models
Chakraborty, S., Shamrat, F. M. J. M., Afrin, S., Saha, S., Ahmed, I., & Thapa, S. (2021) · International Conference on Smart Electronics and Communication (ICOSEC) · doi:10.1109/icosec51865.2021.9591740 · Cited by 7
“Yan et al. [19] initially presented a hierarchical deep-repair neuronal network model to classifying pictures for the hierarchical classification of deep learning.”
Background
Sequence-To-Sequence Neural Networks Inference on Embedded Processors Using Dynamic Beam Search
Pagliari, D. J., Daghero, F., & Poncino, M. (2020) · Electronics · doi:10.3390/electronics9020337 · Cited by 7
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPsPreprint
Zhang, Y., Chen, Z., & Zhong, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03815 · Cited by 11
“Conditional computation methods [7, 8, 9, 10] alleviates this problem via delegation scheme, i.”
BackgroundMethodInfluential
Wrist joint synovial hypertrophy and effusion detection in musculoskeletal ultrasound images using self-attention U-Net
Chang, C.-W., Chang, C., Zhu, Y.-X., & Wang, S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19910-5 · Cited by 6
Amina: an Arabic multi-purpose integral news articles dataset
Zaytoon, M., Bashar, M., Khamis, M. A., & Gomaa, W. E. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10277-0 · Cited by 9
A Two-Stage Lightweight Deep Learning Framework for Mass Detection and Segmentation in Mammograms Using YOLOv5 and Depthwise SegNet
Manolakis, D. E., Bizopoulos, P. A., Lalas, A. X., & Votis, K. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01471-0 · Cited by 8
Hierarchical Deep Learning Model for Identifying Similar Targets in UAV Imagery
Borovyk, D., Barmak, O., Radiuk, P., & Krak, I. V. (2025) · Drones · doi:10.3390/drones9110743 · Cited by 7
“A key feature is the use of two separate deep learning models at each level [38]: one for feature extraction and vector representation, and another for classification based on those features.”
Advanced breath analysis through hierarchical deep convolutional neural network for multi-cancer screening
Lee, B., Lee, J., Noh, H., Bahn, H.-K., Jeon, J.-H., Park, I., Jheon, S., & Lee, D.-S. (2026) · npj Digital Medicine · doi:10.1038/s41746-025-02319-1 · Cited by 6
“This probability integration method was adapted from a previously proposed hierarchical classi ﬁ cation approach 36 .”
Cross-Layer Feature based Multi-Granularity Visual Classification
Chen, J., Chang, D., Xie, J., Du, R., & Ma, Z. (2022) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip56404.2022.10008879 · Cited by 6
“Some methods [2], [4], [5], [18], [19] split the hierarchical classification into several multi-task learning to solve this problem.”
Method
TIC: text-guided image colorization using conditional generative model
Ghosh, S., Roy, P., Bhattacharya, S., Pal, U., & Blumenstein, M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15330-z · Cited by 11
Tomato Leaf Disease Classification with Vision Transformer Variants
Moonwar, W., Mahin, M. R. H., Nadia, Y., Kibria, F. B., Biswas, A., Chowdhury, F. I., Jahan, S. E., & Rasel, A. A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47634-1_8 · Cited by 6
RefinerHash: a new hashing-based re-ranking technique for image retrieval
Sabahi, F., Ahmad, M. O., & Swamy, M. N. S. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01296-x · Cited by 6
Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
Ren, M., Wang, Y., Zhu, Y., Huang, Y., Sun, Z., Li, Q. L., & Tan, T. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02153-0 · Cited by 7
Caption matters: a new perspective for knowledge-based visual question answering
Feng, B., Ruan, S., Wu, L., Liu, H., Zhang, K., Zhang, K., Liu, Q., & Chen, E. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02166-8 · Cited by 6
A comprehensive analysis of DAC-SDC FPGA low power object detection challenge
Zhang, J., Li, G., Zhang, M., Cao, X., Zhang, Y., Li, X., Chen, Z., & Yang, J. (2024) · Science China Information Sciences · doi:10.1007/s11432-023-3958-4 · Cited by 6
Frequency-Domain and Spatial-Domain MLMVN-Based Convolutional Neural Networks
Aizenberg, I. N., & Vasko, A. (2024) · Algorithms · doi:10.3390/a17080361 · Cited by 7
“The use of hierarchical CNNs [34] (that is, the use of a significantly more sophisticated technique) may also boost classification accuracy for the Fashion MNIST dataset [82].”
Method
Multi-modal transformer with language modality distillation for early pedestrian action anticipation
Osman, N., Camporese, G., & Ballan, L. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104144 · Cited by 6
HCAM-CL: A Novel Method Integrating a Hierarchical Cross-Attention Mechanism with CNN-LSTM for Hierarchical Image Classification
Su, J., Liang, J., Zhu, J., & Li, Y. (2024) · Symmetry · doi:10.3390/sym16091231 · Cited by 6
“Early attempts to tackle hierarchical image classiﬁcation (HIC) problems relied on the use of Convolutional Neural Networks (CNNs) [3,12–14].”
Enhancing brain image quality with 3D U-net for stripe removal in light sheet fluorescence microscopy
Li, C., Li, Y., Zhao, H., & Ding, L. (2024) · Brain Informatics · doi:10.1186/s40708-024-00236-9 · Cited by 6
Pix2Gif: Motion-Guided Diffusion for GIF Generation
Kandala, H., Gao, J., & Yang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73013-9_3 · Cited by 6
Multitask learning for automatic detection of meniscal injury on 3D knee MRI
Wang, Y., Ying, M., Yang, Y., Chen, Y., Wang, H., Tsai, T., & Liu, X. (2024) · Journal of Orthopaedic Research® · doi:10.1002/jor.26024 · Cited by 7
Toward Specialized Learning-based Approaches for Visual Odometry: A Comprehensive Survey
Phan, T.-D., & Kim, G.-W. (2025) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-025-02245-0 · Cited by 9
CLIP-driven attention network for multimodal sentiment analysis
Lv, J., Yang, Q., Tian, S., Liu, B., & Yu, L. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07411-7 · Cited by 6
Tree-loss function for training neural networks on weakly-labelled datasets
Demyanov, S., Chakravorty, R., Ge, Z., Bozorgtabar, S., Pablo, M., Bowling, A., & Garnavi, R. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950521 · Cited by 6
“[8] also requires the network to produce a score for coarse labels as well, but additionally fixes the network structure to contain only two levels, which significantly reduces its applicability.”
Background
Weakly labeled fine-grained classification with hierarchy relationship of fine and coarse labels
Jiao, Q., Liu, Z., Ye, L., & Wang, Y. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102584 · Cited by 6
Dysplasia Grading of Colorectal Polyps Through Convolutional Neural Network Analysis of Whole Slide Images
Perlo, D., Tartaglione, E., Bertero, L., Cassoni, P., & Grangetto, M. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3880-0_34 · Cited by 8
“Towards this end, we will follow a hierarchical-like classification approach [26,27], grouping the adenoma classes into high grade (HG) and low grade (LG) dysplasia.”
Method
Research on federated learning method for fault diagnosis in multiple working conditions
Zhou, F., Zhang, Z., & Li, S. (2021) · Complex Engineering Systems · doi:10.20517/ces.2021.08 · Cited by 7
“Yan et al.[26] designed a hierarchical CNN network, with spectral clustering for hierarchical categorizing.”
Background
Improving Image Quality and Reducing Scan Time for Synthetic MRI of Breast by Using Deep Learning Reconstruction
Li, J., Wu, L.-H., Xu, M., Ren, J., Li, Z., Liu, J.-R., Wang, A. J., & Chen, B. (2022) · BioMed Research International · doi:10.1155/2022/3125426 · Cited by 6
Visual Narratives: Large-scale Hierarchical Classification of Art-historical Images
Springstein, M., Schneider, S., Rahnama, J., Stalter, J., Kristen, M., Müller-Budack, E., & Ewerth, R. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00705 · Cited by 6
An Ensemble Model for Combining Deep Matrix Factorization and Image-Based Recommendation Systems
Bao, L. H. Q., Khoa, H. H. B., & Thai-Nghe, N. (2024) · SN Computer Science · doi:10.1007/s42979-024-02978-z · Cited by 6
A Single Hierarchical Network for Face, Action Unit and Emotion Detection
Jyoti, S., Sharma, G., & Dhall, A. (2018) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2018.8615852 · Cited by 6
“[30] proposed a hierarchical network for large scale visual recognition, where easy classes are predicted first and the complex classes are predicted from fine category classifier.”
Background
Fine-Grained Image Classification with Coarse and Fine Labels on One-Shot Learning
Jiao, Q., Liu, Z., Li, G., Ye, L., & Wang, Y. (2020) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew46912.2020.9105959 · Cited by 6
Volumetric Transformer Networks
Kim, S., Susstrunk, S. E., & Salzmann, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58604-1_34 · Cited by 6
Multiple Linear Regression of Multi-class Images in Devices of Internet of Things
Chen, D. (2020) · Traitement du signal · doi:10.18280/ts.370609 · Cited by 6
“[25] 0.85 0.82 0.86 0.81 0.79 0.82 0.86 0.84 0.83 0.81 CNN + Spearmint [26] 0.88 0.86 0.87 0.83 0.80 0.83 0.85 0.86 0.87 0.85 COMO + DropOut [5] 0.90 0.92 0.88 0.87 0.82 0.88 0.86 0.89 0.93 0.91 NIN + DropOut [15] 0.92 0.92 0.96 0.91 0.83 0.92 0.91 0.94 0.89 0.86 AlexNet [1] 0.95 0.93 0.94 0.95…”
BackgroundInfluential
On Expert-Defined Versus Learned Hierarchies for Image Classification
Panchenko, I., & Khan, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37334-4_31 · Cited by 6
Dense Hierarchical CNN – A Unified Approach for Brain Tumor Segmentation
Sille, R., Choudhury, T., Chauhan, P., & Sharma, D. (2021) · Revue d intelligence artificielle · doi:10.18280/ria.350306 · Cited by 6
“Yan et al. [37] proposed a hierarchical deep CNN (HD-CNN) by integrating CNN with the tree structure.”
Method
Neural networks for semantic segmentation of historical city maps: Cross-cultural performance and the impact of figurative diversityPreprint
Petitpierre, R. (2020) · arXiv (Cornell University) · doi:10.13140/rg.2.2.10973.64484 · Cited by 14
Credit Assignment Through Broadcasting a Global Error VectorPreprint
Clark, D. G., Abbott, L. F., & Chung, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.04089 · Cited by 9
“For example, such structure is present in ImageNet [71].”
Background
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images
Nieradzik, L., Stephani, H., Sieburg-Rockel, J., Helmling, S., Olbrich, A., Wrage, S., & Keuper, J. (2024) · Forests · doi:10.3390/f15111910 · Cited by 6
Context-aware coarse-to-fine network for single image desnowing
Cheng, Y., Ren, H., Zhang, R., & Lu, H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17674-y · Cited by 5
A lightweight capsule network via channel-space decoupling and self-attention routing
Guo, Y., Zhang, S., Zhang, C.-M., Gao, H., & Li, H. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18861-1 · Cited by 5
Lightweight 3D-StudentNet for defending against face replay attacks
Seegehalli, P. J., & Krupa, B. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03339-2 · Cited by 5
Dual-scale shifted window attention network for medical image segmentation
Han, D., Yin, X., Xu, J., Li, K., Li, J., Wang, L., & Ma, Z. (2024) · Scientific Reports · doi:10.1038/s41598-024-68587-1 · Cited by 5
Layer-Wise Relevance Propagation with Conservation Property for ResNet
Otsuki, S., Iida, T., Doublet, F., Hirakawa, T., Yamashita, T., Fujiyoshi, H., & Sugiura, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72775-7_20 · Cited by 8
LapUNet: a novel approach to monocular depth estimation using dynamic laplacian residual U-shape networks
Xi, Y., Li, S., Xu, Z., Zhou, F., & Tian, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-74445-x · Cited by 5
End-to-End Deployment of Winograd-Based DNNs on Edge GPU
Mori, P., Rahman, M. S., Frickenstein, L., Sampath, S. B., Thoma, M., Fasfous, N., Vemparala, M. R., Frickenstein, A., Stechele, W., & Passerone, C. (2024) · Electronics · doi:10.3390/electronics13224538 · Cited by 5
Anti-spoofing Approach Using Deep Convolutional Neural Network
Chatterjee, P., & Roy, K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-92058-0_72 · Cited by 5
Class2Str: End to End Latent Hierarchy Learning
Saha, S., Varma, G., & Jawahar, C. V. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546020 · Cited by 5
Hierarchical image-to-image translation with nested distributions modeling
Qiao, S., Wang, R., Shan, S., & Chen, X. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110058 · Cited by 5
“…et al. (2013), making use of category relation graphs Deng et al. (2014); Ding et al. (2015), and improving recognition performance as additional supervision Zhao et al. (2011); Srivastava & Salakhutdinov (2013); Hwang & Sigal (2014); Yan et al. (2015); Goo et al. (2016); Ahmed et al. (2016).”
Enhance Feature Representation of Dual Networks for Attribute Prediction
Fang, Y., Cao, Y., Zhang, W., & Yuan, Q. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-36808-1_2 · Cited by 5
DivNet: Efficient Convolutional Neural Network via Multilevel Hierarchical Architecture Design
Kaddar, B., Fizazi, H., Hernández-Cabronero, M., Sánchez, V., & Serra-Sagrista, J. S. (2021) · IEEE Access · doi:10.1109/access.2021.3099952 · Cited by 5
“To achieve this, we consider a hierarchical structure that has been shown to perform better than the standard architecture –with simply stacked layers– in terms of complexity and performance [7], [8], [41].”
BackgroundMethod
Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
Kondo, K., & Hasegawa, T. (2021) · Sensors · doi:10.3390/s21227743 · Cited by 5
“Similar to B-CNNs, various methods have been proposed to reﬂect the hierarchical structure of classes in CNN models [23–26].”
Hierarchical neural network with efficient selection inference
Mi, J., Li, N., Huang, K.-Y., Li, W., & Zhou, L. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.02.015 · Cited by 6
Exigent Examiner and Mean Teacher: An Advanced 3D CNN-Based Semi-Supervised Brain Tumor Segmentation Framework
Wang, Z., & Voiculescu, I. D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44917-8_17 · Cited by 5
Dynamic Hand Gesture Recognition for Indian Sign Language using Integrated CNN-LSTM Architecture
Patel, P., & Patel, N. M. (2023) · INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING · doi:10.47164/ijngc.v14i4.1039 · Cited by 5
Local Brightness Normalization for Image Classification and Object Detection Robust to Illumination Changes
Lu, Y., Tanaka, M., Kawakami, R., & Okutomi, M. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-0376-0_5 · Cited by 5
Statistical analysis of effective crack properties by microstructure reconstruction and phase-field modeling
Seibert, P., Hirsch, W., Kluge, M., Kalina, M., Kalina, K. A., & Kästner, M. (2024) · Archive of Applied Mechanics · doi:10.1007/s00419-024-02588-4 · Cited by 5
APSSF: Adaptive CNN Pruning Based on Structural Similarity of Filters
Geng, L., & Niu, B. (2024) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-024-00518-4 · Cited by 5
An Ensemble Deep Neural Network-Based Method for Person Identification Using Electrocardiogram Signals Acquired on Different Days
Byeon, Y.-H., & Kwak, K.-C. (2024) · Applied Sciences · doi:10.3390/app14177959 · Cited by 5
A lightweight attention-based deep learning facial recognition system for multiple genetic syndromes
Islam, T. U., & Shaikh, T. A. (2024) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00658-y · Cited by 6
Deep learning predicted perceived age is a reliable approach for analysis of facial ageing: A proof of principle study
Turner, C., Pardo, L. M., Gunn, D. A., Zillmer, R., Mekić, S., Liu, F., Ikram, M. A., Klaver, C. C. W., Croll, P. H., Goedegebure, A., et al. (2024) · Journal of the European Academy of Dermatology and Venereology · doi:10.1111/jdv.20365 · Cited by 5
A real-time platform for Spanish Sign Language interpretation
Morillas-Espejo, F., & Martínez-Martín, E. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10776-0 · Cited by 6
Classification and Severity Estimation of Eccentricity Faults in Salient Pole Synchronous Machine Using Deep Learning
Yusuf, L., Shejwalkar, A., Moa, B., & Ilamparithi, T. C. (2025) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2025.3546202 · Cited by 5
Accurate hand contact detection from RGB images via image-to-image translation
Sorli, S., Trinidad, M. C., & Casas, D. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104200 · Cited by 5
Tech-Driven Strategies for Paddy Disease Prevention and Crop Health Optimization
Sharma, M. R. K., Sethi, M. S., & Singh, M. S. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-27399 · Cited by 5
BranchConnect: Image Categorization with Learned Branch Connections
Ahmed, K., & Torresani, L. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00141 · Cited by 6
“BRANCHCONNECT does also considerably better than NofE [1] and HD-CNN [25], which are the most closely related approaches to our own.”
BackgroundMethodResultInfluential
Parallel Convolutional Networks for Image Recognition via a Discriminator
Yang, S., & Peng, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20887-5_38 · Cited by 6
Layer-wise Guided Training for BERT: Learning Incrementally Refined Document Representations
Manginas, N., Chalkidis, I., & Malakasiotis, P. (2020) · Workshop on Structured Prediction for NLP (SPNLP) · doi:10.18653/v1/2020.spnlp-1.7 · Cited by 7
A Malware Classification Method Based on Basic Block and CNN
Chen, J. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63820-7_31 · Cited by 5
Skip-WaveNet: a wavelet based multi-scale architecture to trace snow layers in radar echograms
Varshney, D., Yari, M., Ibikunle, O., Li, J., Paden, J., Gangopadhyay, A., & Rahnemoonfar, M. (2024) · Environmental Data Science · doi:10.1017/eds.2024.25 · Cited by 7
Hierarchical Decomposition of Large Deep Networks
Chennupati, S., Sah, S., Nooka, S. P., & Ptucha, R. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.19.coimg-152 · Cited by 5
Deep Face Model Compression Using Entropy-Based Filter Selection
Han, B., Zhang, Z., Xu, C., Wang, B., Hu, G., Bai, L., Hong, Q., & Hancock, E. R. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68548-9_12 · Cited by 5
Integrating Domain Knowledge into Deep Learning for Skin Lesion Risk Prioritization to Assist Teledermatology Referral
Carvalho, R., Morgado, A. C., Andrade, C., Nedelcu, T., Carreiro, A. V., & Vasconcelos, M. J. M. (2021) · Diagnostics · doi:10.3390/diagnostics12010036 · Cited by 5
Face Attribute Prediction Using Off-The-Shelf Deep Learning NetworksPreprint
Zhong, Y., Sullivan, J., & Li, H. (2016) · arXiv (Cornell University) · Cited by 5
Rearchitecting Classification Frameworks For Increased RobustnessPreprint
Chandrasekaran, V., Tang, B., Papernot, N., Fawaz, K., Jha, S., & Wu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10900 · Cited by 5
“a) Hierarchical Classification: Recent research casts image classification as a visual recognition task [38], [39], [40].”
Background
Un système intelligent pour le classement du café et l'identification des maladies
Wallelign, S. (2020) · theses.fr (ABES) · doi:10.70675/c2c0bf79z5b49z40f3z84b4z3d86cd806e14 · Cited by 5
GradToken: Decoupling tokens with class-aware gradient for visual explanation of Transformer network
Cheng, L., Liang, Y., Lu, Y., & Cheung, Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106837 · Cited by 5
Cross-graph meta matching correction for noisy graph matching
Li, F., Pan, F., Meng, W., Sun, H., Nie, X., Yin, Y., & Lu, X. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104433 · Cited by 4
Task-Incremental Medical Image Classification with Task-Specific Batch Normalization
Xie, X., Xu, J., Hu, P., Zhang, W., Huang, Y., Zheng, W., & Wang, R. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8558-6_26 · Cited by 4

Authors: Yan, Z., Zhang, H., Piramuthu, R., Jagadeesh, V., DeCoste, D., Di, W., & Yu, Y.
Affiliations: University of Illinois Urbana-Champaign (US)
Carnegie Mellon University (US)
eBay (Ireland) (IE)
ORCID: Yan, Zhicheng
Piramuthu, Robinson
Yu, Yizhou
Venue: 2015 IEEE International Conference on Computer Vision (ICCV)
Publisher: IEEE
Published: 2015-12
Pages: 2740-2748
DOI: 10.1109/iccv.2015.314
OpenAlex: W2962860144
Cited by: 936
References: 44
Citations by year: 2026: 19 · 2025: 79 · 2024: 310 · 2023: 142 · 2022: 42 · 2021: 79 · 2020: 103 · 2019: 61 · 2018: 41 · 2017: 43 · 2016: 16 · 2015: 1
FWCI: 13.68
Type: conference paper
Language: en
Open access: closed
Locations: IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
The HKU Scholars Hub (University of Hong Kong) (submittedVersion)
Topics: Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
Keywords: coarse-to-fine classification, large-scale image classification

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

HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks