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 68,301–68,400 of 108,435
PPA Net: The Pixel Prediction Assisted Net for 3D TOF-MRA Cerebrovascular Segmentation
Lee, Z., Liu, T., Zhang, H., et al. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3561146 · Cited by 4
Cui, N., Wu, Y., Xin, G., Wu, J., Zhong, L., & Liang, H. (2025) · IEEE Access · doi:10.1109/access.2025.3567775 · Cited by 4
Generative adversarial network based on CNN classifier predicted scores for image style transfer
Gladence, L. M., Lai, Y.-W., Lee, F.-T., et al. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113303 · Cited by 4
Hybrid Deep Learning Framework for Eye-in-Hand Visual Control Systems
Botezatu, A.-P., Iancu, A.-I., & Burlacu, A. (2025) · Robotics · doi:10.3390/robotics14050066 · Cited by 4
Rosati, R., Fabiani, M., Pierdicca, R., & Mancini, A. (2025) · Integrated Computer-Aided Engineering · doi:10.1177/10692509251340464 · Cited by 4
Crack Assessment Using Cascade Mask R-CNN and Dilation–Erosion Processing Technique
Bae, S., Kim, B., & Cho, S. (2025) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-6528 · Cited by 4
Toward a dynamic tree-Mamba encoder for UAV tracking with vision-language
Du, G., Zhou, P., Yadikar, N., Aysa, A., & Ubul, K. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113731 · Cited by 5
TCE-YOLOv5: Lightweight Automatic Driving Object Detection Algorithm Based on YOLOv5
Wang, H., Yang, Z., Liu, Q., Zhang, Q., & Wang, H. (2025) · Applied Sciences · doi:10.3390/app15116018 · Cited by 4
Enhancing Adversarial Transferability With Alignment Network
Zhi-wei, L., Li, Q., Ren, M., Ru, Y., & Sun, Z. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3574980 · Cited by 5
Agrawal, K. K., & Kumar, G. (2025) · Research in Veterinary Science · doi:10.1016/j.rvsc.2025.105703 · Cited by 5
A systematic review: Brain age gap as a promising early diagnostic biomarker for Alzheimer's disease
Liu, S., Xu, L., Xu, G., Wang, Y., Zhang, G., & He, L. (2025) · Journal of the Neurological Sciences · doi:10.1016/j.jns.2025.123563 · Cited by 7
Component-based BIM-semantic web integration for enhanced robotic visual perception
Zhu, A., Shao, Z., Chai, X., Ma, E., Li, Q., Ye, H., & Zhang, H. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106270 · Cited by 5
Intelligent diagnosis of fatigue cracks in OSDs based on UGW time-frequency characteristics
Zhang, D., Zhang, Q., Lü, Y., Cui, C., & Zhang, Y. (2025) · Journal of Constructional Steel Research · doi:10.1016/j.jcsr.2025.109689 · Cited by 4
Improvement of speed prediction for an urban network under GA-LSTM-CNN method
Hoon, B. S., Quang, D. T., & Trinh, H. T. (2025) · Transportation · doi:10.1007/s11116-025-10641-6 · Cited by 4
“Specifically, the ReLU function demonstrates superior convergence per - formance in deep neural networks compared to the tanh function (Krizhevsky et al. 2017 ).”
PCLC-Net: Parallel Connected Lateral Chain Networks for Infrared Small Target Detection
Xu, J., Han, X., Wang, J., Feng, X., Li, Z., & Pan, F. (2025) · Remote Sensing · doi:10.3390/rs17122072 · Cited by 4
A neural network based on back-propagation and cooperative co-evolution
Gao, Y., Zhang, Y., & Xie, X. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113453 · Cited by 4
Sugarman, P. C., Ferguson, E. L., Alongi, G. C., Schallert, J. P., & Lyn, H. (2025) · The Journal of the Acoustical Society of America · doi:10.1121/10.0036942 · Cited by 5
Sumsion, A. W., & Lee, D.-J. (2025) · Electronics · doi:10.3390/electronics14132665 · Cited by 6
A comprehensive multimodal benchmark of neuromorphic training frameworks for spiking neural networks
Cheng, Y., Hu, W., He, Y., & Huang, J. Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111543 · Cited by 7
Cui, W., Si, J., Zhang, L., Han, L., & Chen, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3585737 · Cited by 4
Grisi, C., Kartasalo, K., Eklund, M., Egevad, L., van der Laak, J. A. W. M., & Litjens, G. J. S. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103663 · Cited by 5
Deep-learning-based buffalo identification through muzzle pattern images
Ermetin, O., & Kahramanlı, H. (2025) · Archives animal breeding/Archiv für Tierzucht · doi:10.5194/aab-68-473-2025 · Cited by 5
“…several well-known architectures of CNNs: – LeNet is one of the earliest CNN structures proposed by LeCun et al. (1998 – AlexNet was proposed in 2012 by Krizhevsky et al. (2017) and became known after competing in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC – ZF Net is an…”
Gao, R., Jiang, C., & Zhang, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130814 · Cited by 4
Li, Z., Liu, Y., Yang, C., Zhou, Y., & Hu, S. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3590929 · Cited by 5
Ding, Y., Hotta, K., Gu, C., Li, A., Yu, J., & Zhang, C. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3592126 · Cited by 7
Domain aware post training quantization for vision transformers in deployment
Wang, L., Zeng, C., Zhang, M., Wu, J., & Nie, L. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112182 · Cited by 4
Qin, X. R., Yang, X. S., & Tang, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112174 · Cited by 5
Wang, Y., Mücher, C. A., Wang, K., Wang, W., & Kooistra, L. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110754 · Cited by 5
A Pluggable Solution For Robust UAV Tracking Against Attacks
Jia, M., Li, Y., Song, H., & Yuan, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3593838 · Cited by 4
An Automated Method for Identifying Voids and Severe Loosening in GPR Images
Chai, Z., Wang, Z., Xu, Z., Feng, Z., & Zhao, Y. (2025) · Journal of Imaging · doi:10.3390/jimaging11080255 · Cited by 4
“For each model, key performance metrics—including mean Average Precision (mAP), mean recall, number of parameters (Params) [29], computational complexity (GFLOPs), inference latency, runtime FPS on GPU/CPU, and memory usage—were comprehensively analyzed for both “cavity” and “severely loosened…”
A Hand Gesture Recognition Model Using Deep Learning Algorithms
Kale, J. R., Yemul, R. M., Vyavahare, S. S., Lobo, L. M. R. J., & Athavale, V. A. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4839-1.ch008 · Cited by 4
Change Detection on Remote Sensing Images Using Multidimensional Attention Network
Zhang, Y., Xue, M., Lu, Y., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3594716 · Cited by 4
Source-free domain adaptation with aligned transfer and self-supervised learning
Weng, Y., Mei, J.-P., Hu, C., et al. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06777-8 · Cited by 4
Zhang, F., Du, Y., Chen, K., Shao, Y., & Liew, S. C. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3595841 · Cited by 8
Neural operator-based haptic sensing along slender rods
Tang, X., Yang, T., Wang, J., et al. (2025) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2025.110699 · Cited by 4
In-Sensor Compressed Imaging with Reconstruction-Free Recognition via Ferroelectric Photodiodes
Yan, T., Cai, Y., Wang, C., et al. (2025) · Nano Letters · doi:10.1021/acs.nanolett.5c03297 · Cited by 4
Feature-level interpretability in transfer learning-based chiller fault diagnosis
Chen, Z., Rezgui, Y., Zhang, R., et al. (2025) · Building and Environment · doi:10.1016/j.buildenv.2025.113527 · Cited by 4
CTC-YOLO: an improved YOLOv11 algorithm for steel surface defect detection
Yang, L., Li, Z., Hu, X., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adf9bf · Cited by 4
A deep learning-based approach for unsafe area prediction in building fire evacuation
Fang, H., Zhang, B., Tam, W. C., Yang, C., & Lo, S. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.113723 · Cited by 4
Estimation of the remaining useful life of aircraft engines using a CNN-LSTM-GRU hybrid model
Patra, K. C., Sethi, R., & Behera, D. K. (2025) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-025-02911-4 · Cited by 6
“Many research and business disciplines, such as computer vision (Krizhevsky et al. 2017), Natural language processing and speech recognition have had great success using CNNs.”
Omar, A. M., Elhadad, M. K., El‐Samrah, M. G., Nagla, T. F., & Mekkawy, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-13794-7 · Cited by 5
Enhancing anomaly detection in plant disease recognition with knowledge ensemble
Dong, J., Zhou, H., Fuentes, A., Yoon, S., & Park, D. S. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1623907 · Cited by 7
A Review of 3D Shape Descriptors for Evaluating Fidelity Metrics in Digital Twin
Khan, M. T. H., Han, S., Jauhar, T. A., & Noh, C. (2025) · Machines · doi:10.3390/machines13090750 · Cited by 4
Zhou, G., Wang, X., Liu, S., Wang, Y., Gao, E., Wu, J., Lu, Y., Yu, L., Wang, W., & Li, K. (2025) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2025.104805 · Cited by 4
Estimating blood pressure using video-based PPG and deep learning
Zaza, G., Casalino, G., Caputo, S. L., & Castellano, G. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105683 · Cited by 6
You look from old classes: Towards accurate few shot class-incremental learning
Hu, Y., Huang, K., Wang, W., et al. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112352 · Cited by 4
Reduced storage direct tensor ring decomposition for convolutional neural networks compression
Gabor, M., & Zdunek, R. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107994 · Cited by 4
Miao, S., Miao, Y., Zhang, C., & Piao, Y. (2025) · Buildings · doi:10.3390/buildings15173086 · Cited by 4
A transformer-based hybrid network for Alzheimer's disease diagnosis via MRI
Hu, Z., Wang, Y., & Li, Y. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105562 · Cited by 5
Monitoring earth’s glacial lakes from space with machine learning
Tom, M., Odermatt, D., David, C. H., Cerbelaud, A., Wade, J., & Frey, H. (2025) · Science of Remote Sensing · doi:10.1016/j.srs.2025.100277 · Cited by 8
Quantum splitting convolutional neural network-based distributed quantum disease detection model
Li, Y., Qi, Z., Li, Y., Yang, H., Shang, R., & Jiao, L. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131410 · Cited by 7
Automatic visual lip reading: A comparative review of machine-learning approaches
Rezaee, K., & Yeganeh, M. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107171 · Cited by 4
Aktaş, A., Serbes, G., & İlhan, H. O. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3173 · Cited by 7
Chen, X., Xia, X., Zhuo, J., et al. (2025) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2025.138733 · Cited by 4
Li, C., Jiao, F., Wu, S., Wang, C., Wei, M., Zhang, S., Wang, L., Huang, Y., Yin, Y., Tian, R., et al. (2025) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-025-07478-7 · Cited by 5
Zhu, C., Liu, N., Li, Z., et al. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2025.107885 · Cited by 4
VulTriNet: A software vulnerability detection method based on tri-channel network
Yang, Y., Yao, Y., Lv, X., & Chen, W. (2025) · Information and Software Technology · doi:10.1016/j.infsof.2025.107893 · Cited by 4
Drone Monitoring and Behavioral Analysis of White-Beaked Dolphins (Lagenorhynchus albirostris)
Lauridsen, D. G., Madsen, N., Pagh, S., Glarou, M., Pertoldi, C., & Rasmussen, M. H. (2025) · Drones · doi:10.3390/drones9090651 · Cited by 4
Li, C., Zhang, Z., Wang, B., et al. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3768152 · Cited by 4
“AlexNet has 8 layers and its structure is simple, but the fully connected layers account for a large proportion and have a large number of parameters [40].”
Montás-Laracuente, N., Delgado-Martos, E., Calvo, C. P., Sidola, G. I., Maitín, A. M., García-Tejedor, Á. J., & Nogales, A. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.114093 · Cited by 7
In‐Situ Trained Microring‐Based Neural Networks for Scalable and Robust Photonic Computing
Zhao, B., Wu, B., Sun, S., Zhang, S., Gao, D., Zhou, H., Dong, J., & Zhang, X. (2025) · Laser & Photonics Review · doi:10.1002/lpor.202501576 · Cited by 4
Arenas-Prado, J. A., Rangel-Rodriguez, A. H., Amézquita-Sánchez, J. P., Granados‐Lieberman, D., Tapia‐Tinoco, G., & Valtierra‐Rodriguez, M. (2025) · Processes · doi:10.3390/pr13092999 · Cited by 4
“Each filter slides across the input performing element-wise multiplications and summations, resulting in a feature map [45].”
Sabahno, H., & Khodadad, D. (2025) · Computers & industrial engineering · doi:10.1016/j.cie.2025.111538 · Cited by 6
“…layers to learn spatial hierarchies from raw image data, has led to remarkable improvements in tasks such as object detection, image segmentation, and enhancement (Simonyan and Zisserman, 2015; He et al., 2016; Krizhevsky et al., 2017; Xu et al., 2022; Shen et al., 2023; Choi et al., 2024).”
Song, X., Zhang, P., Li, X., Hei, X., & Liu, R. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613150 · Cited by 5
Attention-based Deep Feature Class Proximity for Detection of Traffic Anomaly in Imbalanced Dataset
Porwal, S., Singh, P., & Bansal, A. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04798-x · Cited by 4
Ultrasonic Bioacoustics and Deep Learning for Early Plant Disease Prediction
Sahith, R., Gaddam, S. R., Reddy, P. V., Ganesh, D., Kosuri, G. V., & Thanukula, K. L. (2025) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds65426.2025.11167734 · Cited by 7
Sun, Y., Meng, K., Lang, S., et al. (2025) · Italian National Conference on Sensors · doi:10.3390/s25195985 · Cited by 4
“In addition to benchmarking against existing studies, we also reproduced and evaluated three representative deep neural network architectures—AlexNet [39], VGG16 [40], and ResNet18 [41]—as baseline models.”
ELS-YOLO: Efficient Lightweight YOLO for Steel Surface Defect Detection
Zhang, Z., Zhong, G., Ding, P., He, J., Zhang, J., & Zhu, C. (2025) · Electronics · doi:10.3390/electronics14193877 · Cited by 5
Chen, H., Dou, D., Lu, M., Liu, X., Chang, C. K., Zhang, F., Yang, S., Cao, Z., Luan, P., Li, Y., et al. (2025) · Animals · doi:10.3390/ani15192843 · Cited by 4
“More recently, advances in computational power and algorithm development have facilitated the application of machine learning methods to genomic prediction, including random forest (RF) [8], support vector machine (SVM) [9], and neural networks [10].”
Fuster, S., Khoraminia, F., Silva-Rodríguez, J., Kiraz, U., van Leenders, G. J. L. H., Eftestøl, T., Naranjo, V., Janssen, E. A. M., Zuiverloon, T. C. M., & Engan, K. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000972 · Cited by 5
Caro, R. D. C., Orlova, V. P., di Meo, N., & Zalaudek, I. (2025) · JDDG Journal der Deutschen Dermatologischen Gesellschaft · doi:10.1111/ddg.15847 · Cited by 5
Chen, S., Qin, S., Wang, X., et al. (2025) · Agronomy · doi:10.3390/agronomy15102330 · Cited by 4
Li, H., Chen, H., Wang, Y., Zuo, Z., Wang, H., Wu, J., & Yang, G. (2025) · Applied Thermal Engineering · doi:10.1016/j.applthermaleng.2025.128551 · Cited by 4
Hassan, K. M., El-Kammar, R. A., El-Samie, F. E. A., Abdelfatah, R. I., & Saad, R. S. (2025) · IEEE Access · doi:10.1109/access.2025.3618112 · Cited by 5
Ultrasonic phased array virtual source phase shift migration imaging of curved multilayer components
Hu, H., Wang, L., Wu, J., et al. (2025) · NDT & E International · doi:10.1016/j.ndteint.2025.103575 · Cited by 4
Flood Detection and Mapping: A Critical Review of Methods, Challenges and Future Prospects
Bathe, K. D., & Patil, N. S. (2025) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-025-02277-x · Cited by 5
Xu, X., Zheng, Y., Tong, Z., & Zhu, P. (2025) · Structural Health Monitoring · doi:10.1177/14759217251373102 · Cited by 6
Defects detection for railway catenary system with encoder-decoder architecture
Chen, S., Song, Y., Nåvik, P., Rønnquist, A. N., & Frøseth, G. T. (2025) · Railway Engineering Science · doi:10.1007/s40534-025-00400-9 · Cited by 4
LiteCShuffle: a lightweight and efficient deep learning approach for plant disease classification
Duhan, S., Gulia, P., Gill, N. S., Aziz, A. L., Aljuaid, M. M., Banshal, S. K., & Bansal, R. (2025) · Cogent Food & Agriculture · doi:10.1080/23311932.2025.2568197 · Cited by 6
“Group convolution was initially suggested in alexnet architecture (Krizhevsky et al., 2017).”
Du, W., Ren, Z., Li, F., & Lin, Y. (2025) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2025.102176 · Cited by 5
Dhar, T., Parray, R. A., Bashyal, B. M., Nigam, S., Sharma, S., Prajwal, R., Dhanger, P., Singh, A. K., Khura, T. K., & Yeasin, M. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.107739 · Cited by 6
Design and Implementation of a YOLOv2 Accelerator on a Zynq-7000 FPGA
Kim, H. W., & Kim, T.-K. (2025) · Sensors · doi:10.3390/s25206359 · Cited by 4
Goyal, N., Singh, T., & Goraya, M. S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112657 · Cited by 6
Sun, X., Zhang, Z., Yu, W., et al. (2025) · Powder Technology · doi:10.1016/j.powtec.2025.121769 · Cited by 4
Fully automated synthetic BIM dataset generation using a deep learning-based framework
Liang, X., Yabuki, N., & Fukuda, T. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106584 · Cited by 4
The compounding effects of agricultural expansion and snow drought on lake urmia’s drying crisis
Shahbazi, A., Ghale, Y. A. G., Semiz, G. D., Torun, E., Vaheddoost, B., Beirami, N., Ünal, A., Madani, K. M., & AghaKouchak, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-21735-7 · Cited by 4
“CNNs 115 , initially developed for processing visual data, have also been effectively applied for modeling one-dimensional (1D) data types, such as time series and tabular numerical datasets 116 .”
SFA-DETR: An Efficient UAV Detection Algorithm with Joint Spatial–Frequency-Domain Awareness
He, P., & Wang, X. (2025) · Sensors · doi:10.3390/s25216719 · Cited by 4
“Since the introduction of AlexNet [18], CNNs have become the main tool for image processing in deep learning, effectively applied to computer vision related tasks by gradually downsam-pling and extracting high-dimensional features from input images.”
An Explainable YOLO-Based Deep Learning Framework for Pneumonia Detection from Chest X-Ray Images
Ahmed, A., Siam, A. I., Atwa, A. E. M., Atwa, M. A., Abdelrahim, E. M., & Atlam, E.-S. (2025) · Algorithms · doi:10.3390/a18110703 · Cited by 6
“Convolutional Neural Networks (CNNs), in particular, have shown remarkable success in automatically learning complex visual representations from raw image data, thus removing the need for manual feature extraction [6–8].”
Wang, X., Luo, K., Liu, M., et al. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104011 · Cited by 4
A new method for prediction of Vigna mungo millet disease based on deep learning
Kumar, R., Mahanty, C., Panigrahi, B. S., et al. (2025) · Current Plant Biology · doi:10.1016/j.cpb.2025.100562 · Cited by 4
Wang, Y., & Chen, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104051 · Cited by 5
Improving Network Structure for Efficient Classification Network Based on MobileNetV3
Duan, Z., & Liu, H. (2025) · IEEE Access · doi:10.1109/access.2025.3630207 · Cited by 4
Chen, L., Li, D., Wang, X., Shao, P., Zhang, W., Wang, Y., Tian, Y., & Tang, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3607771 · Cited by 7
Ahmed, W., Wang, F., Fatima, K., Zhang, C., & Deng, H. (2025) · Advances in Physics X · doi:10.1080/23746149.2025.2580625 · Cited by 7
PVMNet: A navel orange defect detection algorithm based on Mamba structure
Huang, Y., & Wang, W. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130412 · Cited by 4
Fed-EHP: Efficient and Heterogeneous Privacy-Preserving Personalized Federated Learning
Han, S., Pan, J., Zhao, S., Ren, S., Wang, Z., He, S., Ren, K., Qin, Z., & Chen, X. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3634446 · Cited by 9
A Cross-Channel Parametric CNN Framework for Microwave Topology Modeling
Yang, Y., Zhang, W., Jin, J., Li, Y., Qu, K., Feng, F., Zhang, Z., & Zhang, Q. (2025) · IEEE Transactions on Microwave Theory and Techniques · doi:10.1109/tmtt.2025.3632203 · Cited by 5
Liu, C., Wang, Y., Yang, J. B., Tao, X., & Liu, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113249 · Cited by 4
RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task
Li, C., Wang, R., Yang, X., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3636726 · Cited by 4
Cheng, Y., Zhang, W., Zheng, T., Cui, E., Ma, X., & Zhang, H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3637775 · Cited by 8
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
