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
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%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Convolutional neural networks (CNNs or ConvNets) are a class of deep feed-forward neural networks whose main purpose is to extract spatial patterns from visual input signals [20, 22].”
From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [22]
Citations
Cites
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
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
Cited by
Sorted by citations
Items 901–929 of 929
90s Thai music classification using audio-visual multimodal model
Charntaweekhun, K., Ketchanchai, D., Narapan, J., Wutthijuk, P., Sirintrawutthiwong, S., & Siriborvornratanakul, T. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11328-w
Asterisk Sparse Convolutional Networks for 3D Object Detection
Lu, C., Yang, C., Su, J., He, Y., & Jiang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6596-9_11
Parallel Interpretation Network via Semantic Visual Probe and Counterfactual Verification
Wan, H., Cheng, K., & Zhou, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6576-1_6
Human Interfaces with Machine Learning Recognition Systems
Clarkson, C. (2025) · doi:10.23889/suthesis.69942
Yang, M.-S., Kim, J.-W., & Lee, H.-S. (2025) · Electronics · doi:10.3390/electronics14193942
Efficient convolutional neural architecture for Arabic Sign Alphabet Classification
Rouabhi, S., Azerine, A., Tlemsani, R., & Idoumghar, L. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04963-2
Improving automated prostate pathological grading via confidence filteringPreprint
Fogarty, R., Goldgof, D. B., Hall, L., Dhillon, J., Chumbalkar, V. C., & Balagurunathan, Y. (2025) · medRxiv · doi:10.1101/2025.11.25.25340482
Improved Image Classification using Lightweight Deep Neural Network Enhancements
Pentsos, V., Tragoudas, S., Gowda, K. N., & Schmit, M. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3779421
“The concept of using additional networks to enhance the performance of a primary CNN has been explored in studies such as [7, 11, 23, 29].”
Deep Hierarchy-Aware Segmentation: A Novel Framework for MRIs Brain Tumor Segmentation
Cheng, Y., Liu, Z. C., & Tamura, S. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3645821
“…to represent semantic relationships through their relative positions; ii) Hierarchical losses [33], [34], which are intended to align predictions with the class hierarchy; and iii) Hierarchical architectures [35], [36], which modify the classifier’s structure to conform to the class hierarchy.”
Javanese Script Recognition Using Hierarchical Deep Convolutional Neural Networks
Adipranata, R., Liliana, Mingardi, J. F., & Budhi, G. S. (2025) · International Conference on Artificial Intelligence Technology (ICoAIT) · doi:10.1109/icoait67446.2025.11308866
“Research on Optical Character Recognition (OCR) for Javanese script is also ongoing, aiming to improve the accessibility and usability of historical manuscripts and educational materials [7, 8, 9, 16].”
Guo, G., Zhang, X., Yuan, H., & Song, M. (2026) · Journal of Biological Physics · doi:10.1007/s10867-025-09698-2
Luo, Y., Li, M., Zhang, Y., Zheng, T., Wang, J., Zhang, Y., Yu, H. M., Cao, H., Li, Y., Dai, N., et al. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109743
HierVision: Standardized and Reproducible Hierarchical Sources for Vision Datasets
Kasarla, T., Rooparaghunath, R. H., D’Arrigo, S., Mago, G., Jha, A., Ayoughi, M., Mishra, S. S., Rodriguez, A. M., Long, T., Atigh, M. G., et al. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00076
“The lack of hierarchical usage negatively impacts learning [53, 93, 126], generalization [93], error severity [8], and more.”
Daimari, E., Ratna, P. S., Mouli, P. V. S. S. R. C., & Madhurima, V. (2026) · The European Physical Journal E · doi:10.1140/epje/s10189-026-00567-x
Knowledge is Power: A Knowledge Graph-Based Approach for Mobile Malware Traceability Analysis
Zhang, Y., Xu, G., Feng, R., Li, X., Chen, S., Xing, Z., Bai, Y., Lyu, Y., Gong, W., & Zhao, X. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3673942
“We map the final features to low-dimensional vectors for final classification and input them into a CNN [42].”
Vers l’universalité des représentations visuelle et multimodales
Tamaazousti, Y. (2018) · theses.fr (ABES) · doi:10.70675/6a8e2fd3zb9a1z48cfzadeez002302237caf · Cited by 1
“EM Approach The methods of the second approach [2, 101, 176, 190, 275, 280] give an answer to the limitation highlighted in the previous section.”
MethodInfluentialReconnaissance d'espèces de poissons dans des images vidéo sous marines
Tamou, A. B. (2021) · theses.fr (ABES) · doi:10.70675/fd0f9332zf0bcz48e9z8919zc894aa835586
Venkataramanan, A. (2023) · theses.fr (ABES) · doi:10.70675/874b5830zd89bz4198z8084z00feea8cb28e
Zhao, K., 任和雷, He, W., Zhao, Y., Jiang, J., Yao, W., Gao, W., & Ban, Q. (2026) · Sensors · doi:10.3390/s26113473
“Yan et al. [34] introduced the Hierarchical Deep Convolutional Neural Network (HD-CNN) for large-scale visual recognition.”
Roni, A. D., Mamun, M. A., Shahed, K. M., & Musa, A. K. M. A. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11546063
“In computer vision, hierarchical classification has been used [15][16].”
CONFINE: Confidence-Gated Coarse-to-Fine Neural Inference for Energy-Efficient Edge Classification
Sarvestani, A. S., Gaire, R. R., & Roohi, A. (2026) · International Green and Sustainable Computing Conference · doi:10.1145/3797248.3816064
“Many classification problems exhibit a natural hierarchy [18, 20], in which a coarse semantic category can be identified with substantially less computation than a fine-grained label.”
Activity-Modulated ReLU: Explicit Cross-Layer Dependency for Hierarchical Learning
Lapamnuaypol, J., & Jin’no, K. (2026) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse68839.2026.11597044
“In intermediate layers (3–5), the network undergoes a transitional phase characterized by a sharp increase in suppression followed by relaxation.”
Rethinking Hierarchical Supervision: Revisiting Simplicity in the Era of Strong Visual Backbones
Thelen, P., Wolf, S., & Beyerer, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31654-7_42
COGAM: Coarse-classification Guided Attention Module for Hierarchical Image Classification
Mou, M., & Fu, R. (2026) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1109/eitce70137.2026.11634451
“Yan et al. [10] proposed the Hierarchical Deep Convolutional Neural Network (HD-CNN), which separates coarse classes using a coarse-grained classifier while distinguishing fine classes using multiple fine-grained classifiers.”
Spriet, C., Rostami, F., Hochmann, J., & Papeo, L. (2026) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.a.2721 · Cited by 1
Karthikeyan, S., Cruz, M. V., Ramakrishnan, A. B., & Sumathi, A. C. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-27368-0_21
Coarse-to-Fine Label Distribution Learning for High-Cardinality Survey Simulation
Li, J., Liu, H., Meng, Z., Qiu, C., & Gu, J. (2026) · International Journal of Web Services Research · doi:10.4018/ijwsr.424308
Metadata
- 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)
- Venue
- 2015 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 2740-2748
- 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
