The DOI matches its Crossref record, with a small difference in title or year; 31 of the 31 references it cites were found in a registry or an index; 2 of the 14 sources its claims cite were checked for support.
ImageNet classification with deep convolutional neural networks
Open accessAbstract
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
42 Own result · 21 Own interpretation · 7 No basis given · 4 No full text of the sources · 3 Sources not found · 2 Supported · 2 Not checked yet · 1 Own method
Every source the paper cites for this claim was checked and supports it.
In the paper
“This technique reduces complex co adaptations of neurons, since a neuron cannot rely on the presence of particular other neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper states on p. 1 that dropout prevents complex co-adaptations by randomly omitting hidden units, so a hidden unit cannot rely on other hidden units being present. This directly supports the citing sentence. (LLM, conf=0.95)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is, however, a very efficient version of model combination that only costs about a factor of two during training.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper describes dropout as an efficient way to combine many neural-network models (p. 1). In F.6 Training (p. 17), it reports that ImageNet training took roughly four days with dropout versus two days without it, supporting the approximate factor-of-two training cost. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces our top-1 and top-5 error rates by 1.7% and 1.2%, respectively, as compared with a net with half as many kernels in each convolutional layer trained on one GPU.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The size of our network made overfitting a significant problem, even with 1.2 million labeled training examples”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“So these data augmentation schemes are, in effect, computationally free.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 26
- The quote only partly states this claim. 2
Create a free account to see these claims.
Create a free account to see these assumptions.
34 more claims
Create a free account to see all 82 claims and to verify the 3 references still open.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the field of DL, the CNN is the most famous and commonly employed algorithm [30, 71–75].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep CNN architectures with 8, even 22 layers [4], [33], can be useful even for CADe problems where the available training datasets are limited.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fully convolutional neural networks (fCNNs) have provided state-of-the-art performance for object classification and image segmentation (1).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first wave saw the emergence of deep learning as the dominant paradigm for analyzing high-dimensional biological data.”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [1]
Experimental — accuracy not yet measured
19 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.5. Overall architecture
“The third convolutional layer has 384 kernels of size 3 × 3 × 256”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
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
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,884
Self-citationLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,501
Self-citation(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Self-citationFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Research works printed but not linked: 13
- Berg A., 2010, Large scale visual recognition challenge
- Deng J., 2009, CVPR09
- Krizhevsky A., 2009, Department of Computer Science
- Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript
- Krizhevsky A., 2011, ESANN
- LeCun Y., 1990, Advances in Neural Information Processing Systems
- LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)
- 10.5555/1896300.1896315 · DOI
- Mensink T., 2012, Italy
- 10.5555/3104322.3104425 · DOI
- Rumelhart D.E., 1985, DTIC Document
- 10.5555/938980.939477 · DOI
- Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences
Cited by
Items 65,001–65,100 of 108,435
Identifying Eclipsing Binary Stars with TESS Data Based on a New Hybrid Deep Learning Model
Shan, Y., Chen, J., Zhang, Z., et al. (2025) · Publications of the Astronomical Society of the Pacific · doi:10.1088/1538-3873/adc5a2 · Cited by 5
Big-data-driven vessel destination prediction for smart port management
Chen, J., Zhang, Q., Liang, M., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110829 · Cited by 5
Li, N., Wu, Y., Jiang, Z., et al. (2025) · Horticulturae · doi:10.3390/horticulturae11050489 · Cited by 5
Deep Watermarking Based on Swin Transformer for Deep Model Protection
Un, C.-H., & Choi, K.-C. (2025) · Applied Sciences · doi:10.3390/app15105250 · Cited by 5
AlzClassNet: A Hybrid CNN-Transformer Model for Alzheimer’s Disease Detection and Staging
Chakraborty, G., Sushant, Das, N., Raj, R., verma, K., & Prakash, A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.264 · Cited by 6
Tracing human genetic histories and natural selection with precise local ancestry inference
Lerga-Jaso, J., Novković, B., Unnikrishnan, D., Bamunusinghe, V., Hatorangan, M. R., Manson, C., Pedersen, H., Osama, A., Terpolovsky, A., Bohn, S., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-59936-3 · Cited by 13
Revolutionizing Data Preparation And Access For Visual And Multi-Modal Business Analytics
-, O. L. (2025) · International Journal on Science and Technology · doi:10.71097/ijsat.v16.i2.3490 · Cited by 5
A multiscale brain emulation-based artificial intelligence framework for dynamic environments
Xie, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-01431-2 · Cited by 5
V-STAR: A Cloud-Based Tool for Satellite Detection and Mapping of Volcanic Thermal Anomalies
Cariello, S., Malaguti, A. B., Corradino, C., et al. (2025) · GeoHazards · doi:10.3390/geohazards6020024 · Cited by 5
Luan, T., Zhou, S. K., Zhang, Y., et al. (2025) · Mathematics · doi:10.3390/math13111825 · Cited by 5
A Complete System for Automated Semantic–Geometric Mapping of Corrosion in Industrial Environments
de Figueiredo, R. P., Eriksen, S. N., Bøgh, S., & Rodríguez, I. (2025) · Automation · doi:10.3390/automation6020023 · Cited by 5
Contreras, K., Gutierrez-Rengifo, J., Casanova-Carvajal, Ó., Álvarez, A. L., Vélez-Varela, P. E., & Bojorge, A. L. U. (2025) · Applied Sciences · doi:10.3390/app15116274 · Cited by 5
The Genesis and Evolution of AI Agents
Huang, K. (2025) · Progress in IS · doi:10.1007/978-3-031-90026-6_1 · Cited by 5
Yeh, W., Shia, W.-C., Hsu, Y.-T., Huang, C.-H., & Lee, Y. (2025) · Bioengineering · doi:10.3390/bioengineering12060640 · Cited by 6
“Due to the limited number of images in commonly used mammographic datasets, researchers employ data augmentation techniques to increase the amount of training data in order to prevent model overfitting [8] and to enhance the model’s generalization ability.”
Cossio, M., Wiedemann, N., Torres, E. S., Sole, E. B., & Igual, L. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1598289 · Cited by 5
Motor Imagery Classification Based on Temporal-Spatial Domain Adaptation for Stroke Patients
Ma, J., Zhang, J., Yang, Y., et al. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10477-3 · Cited by 5
Xu, H., Song, Y., Xu, G., et al. (2025) · Sensors · doi:10.3390/s25123769 · Cited by 5
Maryada, S. K., Devegowda, D., Rai, C., Curtis, M. E., Ebert, D. S., & Danala, G. (2025) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2025.214043 · Cited by 5
Transfer Learning Fusion Approaches for Colorectal Cancer Histopathological Image Analysis
ALGhafri, H. S., & Lim, C. S. (2025) · Journal of Imaging · doi:10.3390/jimaging11070210 · Cited by 7
“A notable decrease in error rates was reported in the ImageNet Large Scale Visual Recognition Competition (ILSVRC) [2].”
Artificial intelligence techniques in inherited retinal diseases: a review
Trinh, H., Vice, J., Tajbakhsh, Z., Charng, J., Alam, K., Chen, F. K., & Mian, A. S. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ade9c7 · Cited by 9
Feng, T., Wang, Z., Qiu, L., et al. (2025) · Sensors · doi:10.3390/s25134091 · Cited by 5
“The selected models include representative convolutional neural networks such as AlexNet [31], MobileNet-V2 [32], and EfficientNet-b0 [33], as well as Vision Transformer-based architectures and their variants, namely ViT-Base [34], ConvNeXt-T [35], and SwinT [36].”
Madokoro, H., & Nix, S. (2025) · Sensors · doi:10.3390/s25134053 · Cited by 7
“While the backbone of convolutional neural networks (CNNs) was proposed over 30 years ago [9], the development of multilayered architectures and the subsequent deep learning boom began a decade ago [10].”
Huang, Q., Luo, Y., Liu, Z., Xia, J., Chang, M., & Li, J. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13071271 · Cited by 6
Tong, D., Han, H., Li, C., Wang, F., Kong, W., & Ren, N. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104139 · Cited by 5
Tampu, I. E., Nyman, P. O., Spyretos, C., Blystad, I., Shamikh, A., Prochazka, G., de Ståhl, T. D., Sandgren, J., Lundberg, P., & Haj‐Hosseini, N. (2025) · Brain Pathology · doi:10.1111/bpa.70029 · Cited by 7
Bouallègue, B., El-Latif, Y. M. A., El-Sofany, H. F., & Taj-Eddin, I. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/8884481 · Cited by 8
Impact of Data Quality on CNN-Based Sewer Defect Detection
Jang, S.-W., & Kim, D. (2025) · Water · doi:10.3390/w17132028 · Cited by 4
Sklab, Y., Ariouat, H., Chenin, E., Prifti, E., & Zucker, J. (2025) · IET Computer Vision · doi:10.1049/cvi2.70036 · Cited by 9
Real-Time Progress Monitoring of Bricklaying
Magdy, R., Hamdy, K., & Essawy, Y. A. S. (2025) · Buildings · doi:10.3390/buildings15142456 · Cited by 8
LLM-driven semantic explanations for soil moisture prediction models
Koné, B. A. T., Boukadi, K., Grati, R., Abdallah, E. B., & Mecella, M. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101174 · Cited by 7
Blind source separation of single-channel mixtures via multi-encoder autoencoders
Webster, M. B., & Lee, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131008 · Cited by 7
RegPalm: Toward Large-Scale Open-Set Palmprint Recognition by Reducing Pattern Variance
Zhong, Y., Chai, W., Wang, L., Zheng, D., Fu, H., & Ma, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3593352 · Cited by 5
Kim, H. B., Tan, H. Q., Nei, W. L., Tan, Y., Cai, Y., & Wang, F. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01844-5 · Cited by 5
“…of backpropagation in neural networks, a foundational yet crucial aspect of modern DL. Computer Vision (CV) models showed promising results with the introduction of AlexNet [13] where it surpassed previous CV models by a huge margin in performance in the ImageNet classification challenge [14].”
Salloum, S. A. (2025) · JMIR Formative Research · doi:10.2196/71974 · Cited by 6
“The assessment of histopathological slides, ultrasound scans, mammograms, and other breast cancer images is made using CNNs [7,8].”
Multi-Strategy Fusion RRT-Based Algorithm for Optimizing Path Planning in Continuous Cherry Picking
Zhang, Y., Miao, X., Sun, Y., et al. (2025) · Agriculture · doi:10.3390/agriculture15151699 · Cited by 5
Towards Stable WiFi-based HAR from Imbalanced Data and Changing Circumstances
Wang, Y., Zhou, Z., Wang, S., et al. (2025) · ACM Transactions on Sensor Networks · doi:10.1145/3757321 · Cited by 5
“— CNN [29]: CNN is trained using only source-domain samples and then the target-domain data is used to evaluate the effectiveness of the training.”
InfluentialSoni, K., & Gangwar, R. C. (2025) · Planta · doi:10.1007/s00425-025-04797-9 · Cited by 7
Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
Xie, F., Nie, J., Tan, Y., Zhang, W., & Zhao, H. (2025) · 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/cvpr52734.2025.01874 · Cited by 8
Ammar, M., Javaid, N., & Arishi, A. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.07.040 · Cited by 7
Tang, Y., Wei, Y., Hu, Y., Zheng, X., & Ji, C. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3761818 · Cited by 6
“For this objective, we adopt the principle of channel separation in group convolution [27, 65].”
Pavement Friction Prediction Based Upon Multi-View Fractal and the XGBoost Framework
Peng, Y. L., Kai, J., Yu, X., Zhang, Z., Li, Q., Yang, G., & Kong, L. (2025) · Lubricants · doi:10.3390/lubricants13090391 · Cited by 6
Shifted windowing vision transformer-based skin cancer classification via transfer learning
Lian, J., Han, L., Wang, X., Ji, Z., & Lei, C. (2025) · Clinics · doi:10.1016/j.clinsp.2025.100724 · Cited by 5
YOLO-UAVShip: An Effective Method and Dateset for Multi-View Ship Detection in UAV Images
Li, Y., Tian, Y., Yuan, C., Yu, K., Yin, K., Huang, H., Yang, G., Li, F., & Zhou, Z.-G. (2025) · Remote Sensing · doi:10.3390/rs17173119 · Cited by 8
Majidiyan, H., Enshaei, H., & Howe, D. (2025) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2025.3596359 · Cited by 5
Characterising the neural time-courses of food attribute representations
Chae, V. J., Grootswagers, T., Bode, S., & Feuerriegel, D. (2025) · Appetite · doi:10.1016/j.appet.2025.108337 · Cited by 4
A comprehensive survey of image clustering based on deep learning
Hou, H., Ding, S., Cao, C. G., et al. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112590 · Cited by 5
Object Discovery Using CNN Features in Egocentric Videos
Bolaños, M., Garolera, M., & Radeva, P. I. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19390-8_8 · Cited by 5
Network in network based weakly supervised learning for visual tracking
Chen, Y., Yang, X., Zhong, B., Zhang, H., & Lin, C. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.10.004 · Cited by 5
Scalable logo recognition based on compact sparse dictionary for mobile devices
Tang, S., Zhang, Y., & Chen, H. (2015) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2015.7340863 · Cited by 5
Efficient aspect object models using pre-trained convolutional neural networks
Wilkinson, E., & Takahashi, T. (2015) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2015.7363556 · Cited by 5
Unified Virtual Memory Support for Deep CNN Accelerator on SoC FPGA
Xiao, T., Qiao, Y., Shen, J., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27119-4_5 · Cited by 5
Convolutional autoencoder-based color image classification using chroma subsampling in YCbCr space
Li, Z., Fan, Y., & Wang, F. (2015) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2015.7407903 · Cited by 6
He, J. Y. D., Shang, X., Zhang, H., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27674-8_44 · Cited by 5
Automatic detection of necrosis, normoxia and hypoxia in tumors from multimodal cytological images
Carneiro, G., Peng, T., Bayer, C., et al. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351238 · Cited by 5
Spoerer, C. J., Eguchi, A., & Stringer, S. M. (2016) · Vision Research · doi:10.1016/j.visres.2015.12.008 · Cited by 5
BVCNN: A Multi-object Image Recognition Method Based on the Convolutional Neural Networks
Shi, H., Mu, X., & Wang, S. (2015) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv.2015.28 · Cited by 5
Ordering of Visual Descriptors in a Classifier Cascade Towards Improved Video Concept Detection
Markatopoulou, F., Mezaris, V., & Patras, I. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-27671-7_73 · Cited by 5
Weighing classes and streams: toward better methods for two-stream convolutional networks
Kim, H., Uh, Y., Ko, S., & Byun, H. (2016) · Optical Engineering · doi:10.1117/1.oe.55.5.053108 · Cited by 5
Towards More Natural Social Interactions of Visually Impaired Persons
Carrato, S., Fenu, G., Medvet, E., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25903-1_63 · Cited by 5
Laplacian pyramids for deep feature inversion
Singh, A., & Namboodiri, A. (2015) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2015.7486511 · Cited by 5
Visual Target Sequence Prediction via Hierarchical Temporal Memory Implemented on the iCub Robot
Kırtay, M., Falotico, E., Ambrosano, A., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-42417-0_12 · Cited by 5
Speeding-up a convolutional neural network by connecting an SVM network
Pasquet, J., Chaumont, M., Subsol, G., et al. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532766 · Cited by 5
On CPU Performance Optimization of Restricted Boltzmann Machine and Convolutional RBM
Wicht, B., Fischer, A., & Hennebert, J. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46182-3_14 · Cited by 5
Gaze latent support vector machine for image classification
Wang, X., Thome, N., & Cord, M. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532354 · Cited by 6
Iterative localization refinement in convolutional neural networks for improved object detection
Cheng, K., Chen, Y., & Fang, W. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533039 · Cited by 5
Face detection algorithm based on a cascade of ensembles of decision trees
Lebedev, A., Pavlov, V. A., Хрящев, В. В., & Stepanova, O. (2016) · Conference of Open Innovations Association (FRUCT) · doi:10.1109/fruct-ispit.2016.7561522 · Cited by 5
Improving the similarity estimation via score distribution
Liao, L., Wei, S., Zhao, Y., et al. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552945 · Cited by 5
Detection of Abnormalities in Driving Style Based on Moving Object Trajectories without Labels
Huang, T.-H., Nikulin, V., & Chen, L.-B. (2016) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai.2016.92 · Cited by 5
Exploiting multiple contexts for saliency detection
Du, M., Wu, X., Chen, W., & Wang, J. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.6.063005 · Cited by 5
Peripheral pooling is tuned to the localization task
Eberhardt, S., Zetzsche, C., & Schill, K. (2016) · Journal of Vision · doi:10.1167/16.2.14 · Cited by 7
Sparse Coding Based Fisher Vector Using a Bayesian Approach
Lim, K., & Wang, H. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2636900 · Cited by 5
Automatic Discovery of Discriminative Parts as a Quadratic Assignment Problem
Sicre, R., Rabin, J., Avrithis, Y., et al. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.129 · Cited by 5
Tanno, R., & Yanai, . (2016) · doi:10.1145/3004010.3004025 · Cited by 5
Sparse Wavelet Auto-Encoders for Image Classification
Hassairi, S., Ejbali, R., & Zaied, M. (2016) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2016.7797085 · Cited by 5
Text Deblurring Using OCR Word Confidence
Verma, A., & Singh, D. K. (2017) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2017.01.05 · Cited by 5
Image Operator Learning and Applications
Montagner, I. D. S., Hirata, N. S. T., & Hirata, R. (2016) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi-t.2016.013 · Cited by 4
Pipeline-based processing of the deep learning framework caffe
Ayae, I., Takefusa, A., Nakada, H., & Oguchi, M. (2017) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1145/3022227.3022323 · Cited by 5
The recognition of Chinese caption text in news video using convolutional neural network
Zhong, D., Shi, P. A., Pan, D., & Yuan, S. (2016) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec.2016.7867291 · Cited by 4
Multiple hierarchical deep hashing for large scale image retrieval
Cao, L., Gao, L., Song, J., Shen, F., & Wang, Y. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4489-0 · Cited by 4
Discriminative restricted Boltzmann machine for emergency detection on healthcare robot
Kim, H., Han, S. H., & Choi, H.-J. (2017) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp.2017.7881745 · Cited by 5
Rotative maximal pattern: A local coloring descriptor for object classification and recognition
Pang, J., Huang, J., Qin, L., Zhang, W., Qing, L., Huang, Q., & Yin, B. (2017) · Information Sciences · doi:10.1016/j.ins.2017.04.011 · Cited by 5
A multi-modal RGB-D object recognizer
Fäulhammer, T., Zillich, M., Prankl, J., et al. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899722 · Cited by 5
Deep Learning Techniques for Roadside Video Data Analysis
Verma, B., Zhang, L., & Stockwell, D. R. B. (2017) · Studies in computational intelligence · doi:10.1007/978-981-10-4539-4_4 · Cited by 5
Adaptive hierarchical classification networks
Nooka, S. P., Chennupati, S., Veerabhadra, K., Sah, S., & Ptucha, R. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900189 · Cited by 5
A feature embedding strategy for high-level CNN representations from multiple convnets
Akilan, T., Wu, Q. M. J., & Jiang, W. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309150 · Cited by 5
Robust visual tracking with deep feature fusion
Wang, G., Wang, J., Tang, W., & Yu, N. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952490 · Cited by 5
Power difference template for action recognition
Wang, L., Li, R., & Fang, Y. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0848-0 · Cited by 5
McWhirter, P. R., Steele, I. A., Al‐Jumeily, D., et al. (2017) · doi:10.1109/ijcnn.2017.7966236 · Cited by 5
LASSO approximation and application to image super-resolution with CUDA acceleration
Tan, H., Xiao, H., Liu, Y., et al. (2017) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc.2017.7984603 · Cited by 5
On How to Design Dataflow FPGA-Based Accelerators for Convolutional Neural Networks
Natale, G., Bacis, M., & Santambrogio, M. D. (2017) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi.2017.126 · Cited by 5
Classifying Non-linear Gene Expression Data Using a Novel Hybrid Rotation Forest Method
Lu, H., Meng, Y., Yan, K., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-63315-2_64 · Cited by 5
Region similarity arrangement for large-scale image retrieval
Zhang, D., Tang, J., Jin, G., et al. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.07.025 · Cited by 5
Incomplete Attribute Learning with auxiliary labels
Liang, K., Guo, Y., Chang, H., et al. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/313 · Cited by 5
Learning to Count Mosquitoes for the Sterile Insect Technique
Ovadia, Y., Halpern, Y., Krishnan, D., Livni, J., Newburger, D. E., Poplin, R. E., Zha, T., & Sculley, D. (2017) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3097983.3098204 · Cited by 5
Bioinspired vision-only UAV attitude rate estimation using machine learning
Merida-Floriano, M., Caballero, F., García-Morales, D., Casares, F., & Merino, L. (2017) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2017.7991430 · Cited by 5
Bit-width reduction and customized register for low cost convolutional neural network accelerator
Choi, K., Choi, W., Shin, K., & Park, J. (2017) · International Symposium on Low Power Electronics and Design (ISLPED) · doi:10.1109/islped.2017.8009164 · Cited by 5
Memory-optimal neural network approximation
Gitta Kutyniok, B., Grohs, P., Petersen, P., & Bölcskei, H. (2017) · Wavelets and Sparsity · doi:10.1117/12.2272490 · Cited by 6
Memory-based pedestrian detection through sequence learning
Li, X., Ye, M., Liu, Y., & Zhu, C. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019420 · Cited by 5
A fast image retrieval method with convolutional neural networks
Yao, J., Deng, Y., Yao, Y., et al. (2017) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2017.8029131 · Cited by 5
Derivative-based acceleration of general vector machine
Yong, B., Li, F., Lv, Q., Shen, J., & Zhou, Q. (2017) · Soft Computing · doi:10.1007/s00500-017-2808-z · Cited by 5
Metadata
- Authors
- Krizhevsky, A., Sutskever, I., & Hinton, G. E.
- Affiliations
- Google (United States) (US)
- University of Toronto (CA)
- Venue
- Communications of the ACM
- Published
- 2017-05-24
- Volume
- 60
- Issue
- 6
- Pages
- 84-90
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2163605009
- Cited by
- 112,155
- References
- 27
- Citations by year
- 2026: 2710 · 2025: 7710 · 2024: 10211 · 2023: 12267 · 2022: 12280 · 2021: 15497 · 2020: 14538 · 2019: 13976 · 2018: 9999 · 2017: 6661
- FWCI
- 5127.18
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- neural information processing systems
- 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
- ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
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.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
