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 61,301–61,400 of 108,437
A Terrain-Aided Navigation Method Incorporating Terrain Matching and Terrain Suitability Analysis
Fan, G., Liu, X., Li, Y., Li, J., Han, Y., He, L., & Chen, P. (2025) · IEEE Access · doi:10.1109/access.2025.3562768 · Cited by 6
TRGNet: a deep transfer learning approach for software defect prediction
Nevendra, M., & Singh, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127799 · Cited by 6
Li, Y., Zhou, R., Zhou, Y., & Chen, Z. S. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110395 · Cited by 7
Guan, Y., Liu, Y., Wang, J., Wang, T., Yi, Q., Jiang, W., Gu, X., Zhang, Y., Zhang, L., Han, T., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3565002 · Cited by 9
Channel-shuffled transformers for cross-modality person re-identification in video
Kasantikul, R., Kusakunniran, W., Wu, Q., & Wang, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-00063-w · Cited by 6
DMSA-Net: a deformable multiscale adaptive classroom behavior recognition network
Dong, C., Liu, J., & Xie, S. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2876 · Cited by 7
Yamaguchi, S., Isokawa, T., Matsui, N., Kamiura, N., & Tsuruyama, T. (2025) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf137 · Cited by 9
Jadayel, M., & Khameneifar, F. (2025) · Machines · doi:10.3390/machines13050382 · Cited by 9
Group equivariant learning for few-shot image classification
Su, M., Yan, L., & Li, F. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06546-7 · Cited by 6
Deep learning delineates alluvial fans driven by topographic knowledge and imagery
Huang, T., Cao, H., & Xiong, L. (2025) · CATENA · doi:10.1016/j.catena.2025.109089 · Cited by 6
Identifying different classes of geoacoustic events using machine learning
Wang, J., Zuo, Y., Dong, L., & Yan, X. (2025) · International Journal of Rock Mechanics and Mining Sciences · doi:10.1016/j.ijrmms.2025.106144 · Cited by 7
Deep Learning-Based Classification of Canine Cataracts from Ocular B-Mode Ultrasound Images
Park, S., Go, S., Kim, S., & Shim, J. (2025) · Animals · doi:10.3390/ani15091327 · Cited by 12
Uddin, M. J., Gholap, A. D., Khan, T., Proma, A. Y., Masud, S., Choonara, Y. E., Gowri, S. S., Webster, T. J., & Faiyazuddin, M. (2024) · Journal of Biomedical Nanotechnology · doi:10.1166/jbn.2024.3933 · Cited by 8
Dynamic Multi-Behaviour, Orientation-Invariant Re-Identification of Holstein-Friesian Cattle
Perneel, M., Adriaens, I., Verwaeren, J., & Aernouts, B. (2025) · Sensors · doi:10.3390/s25102971 · Cited by 9
Ngartera, L., & Nadarajah, S. (2025) · Frontiers in Built Environment · doi:10.3389/fbuil.2025.1597255 · Cited by 9
Ibarra, J. P. G., Cuevas, F. J., & Vidales, J. R. H. (2025) · Horticulturae · doi:10.3390/horticulturae11050514 · Cited by 10
Multi-phase segmentation methods for micro-tomographic images based on deep learning
Yu, Y., Wei, W., Cui, W., Cheng, W., Zang, J., Fang, L., & Zheng, L. (2025) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2025.213962 · Cited by 6
Kan, Y., Liu, X., & Liu, H. (2025) · Aerospace · doi:10.3390/aerospace12050434 · Cited by 7
High-Speed Cyclic Voltammetry Regressions Using Machine Learning
Rosser, D. A., & Leonard, K. C. (2025) · ACS electrochemistry. · doi:10.1021/acselectrochem.5c00012 · Cited by 8
MSPE-Fusion: A multimodal 3D object detection method with multi-sensor perception enhanced fusion
Yu, S., Wang, X., Ci, Y., Li, Y., Zhou, M., Dong, X., & Cai, M. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130486 · Cited by 9
Rakhilin, N., Morris, H. D., Pham, D. L., Hood, M. N., & Ho, V. B. (2025) · Bioengineering · doi:10.3390/bioengineering12050519 · Cited by 10
Versatile and Robust Reservoir Computing with PWM‐Driven Heterogenous R – C Circuits
Ma, Z., Yi, H., Zheng, Z., Chen, Z., Liu, W., Chen, Y., Cheng, B., Cai, C., Pan, S., & Ge, J. (2025) · Advanced Science · doi:10.1002/advs.202416413 · Cited by 7
Zeng, H., Zou, S., Yao, C., & Xu, C. (2025) · Symmetry · doi:10.3390/sym17050780 · Cited by 6
A multi-level graph-based surrogate model for real-time high-fidelity sheet forming simulations
Zhou, H., Zhao, Y., Li, H., et al. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103458 · Cited by 6
Lee, O. V., & Joo, H. (2025) · Electronics · doi:10.3390/electronics14102082 · Cited by 6
AI-Driven Toolbox for Efficient and Transferable Visual Quality Inspection in Production
Trampert, P., Mantowsky, S., Schmidt, F., Masiak, T., & Schneider, G. (2025) · SN Computer Science · doi:10.1007/s42979-025-03988-1 · Cited by 10
Qin, H., Yu, L., Tian, S., Zhou, C., Yu, Y., & Zhang, L. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113707 · Cited by 7
Lin, S., Dong, M., Guo, H., Zheng, L., Zhao, K., & Zheng, H. (2025) · Journal of Rock Mechanics and Geotechnical Engineering · doi:10.1016/j.jrmge.2025.02.023 · Cited by 7
Raj, Y. A., Sunitha, P., Malaiarasan, A., & Farhaoui, Y. (2025) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-025-00826-1 · Cited by 6
A comprehensive review of on-board action recognition models in public transportation systems
Meurie, C., & Lézoray, O. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128311 · Cited by 9
Ghayoumi, M. (2025) · AI · doi:10.3390/ai6060111 · Cited by 8
Sillaparaya, A., Jiraraksopakun, Y., Chamnongthai, K., & Bhatranand, A. (2025) · IEEE Access · doi:10.1109/access.2025.3575203 · Cited by 6
Petrus, M., Popa, C., Bratu, A., Bercu, V., Gebac, L. C., Mihai, D.-M., Butcaru, A.-C., Stănică, F., & Gogoț, R. (2025) · Molecules · doi:10.3390/molecules30112431 · Cited by 8
“…work has also demonstrated the importance of selecting appropriate network architectures, implementing dropout regularization, and using data augmentation strategies (e.g., image flipping, rotation, brightness normalization) to enhance generalization performance and reduce overfitting [26,27].”
Partheepan, S., Sanati, F., & Hassan, J. A. (2025) · IEEE Access · doi:10.1109/access.2025.3577251 · Cited by 6
Molina-Tenorio, Y., Prieto‐Guerrero, A., Rodríguez-Colina, E., Vásquez-Toledo, L. A., & Olvera-Guerrero, O. A. (2025) · Sensors · doi:10.3390/s25123580 · Cited by 6
“In recent years, CNNs [25] have emerged as a key tool in deep learning, especially for image processing, allowing for the efficient identification of relevant patterns and features, for example, in object recognition, image segmentation, and visual analysis tasks [26,27].”
Abdalla, A., Mohammed, M. M. A., Adedeji, O., Dotray, P. A., & Guo, W. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101086 · Cited by 6
An end-to-end deep learning solution for automated LiDAR tree detection in the urban environment
Rice, J. R., Fricker, G. A., & Ventura, J. (2025) · ISPRS Open Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.ophoto.2025.100092 · Cited by 7
Sarthak, S., & Srinivasacharya, D. (2025) · European Journal of Mechanics - B/Fluids · doi:10.1016/j.euromechflu.2025.204307 · Cited by 6
Dang, V. N., Hoang, N. C., Nguyen, Q. C., et al. (2025) · Measurement · doi:10.1016/j.measurement.2025.118056 · Cited by 6
Lu, Q., Chen, X., Yin, Y., Feng, B., Yan, J., & Su, Q. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121901 · Cited by 7
Ma, H., Lei, S., Li, H.-C., & Çelik, T. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103371 · Cited by 8
Yang, Y., He, L., Li, W., Yang, K., Liu, Y., Luo, J., & Wang, J. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121814 · Cited by 7
Kao, J.-P., Chung, Y.-C., Hung, H.-Y., Chen, C., & Chen, W. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102583 · Cited by 7
Machine learning and partial differential equations: benchmark, simplify, and discover
Koumoutsakos, P. (2025) · Data-Centric Engineering · doi:10.1017/dce.2025.15 · Cited by 8
Safarov, F., Kutlimuratov, A., Khojamuratova, U., et al. (2025) · Sensors · doi:10.3390/s25123832 · Cited by 6
OptiPIM: Optimizing Processing-in-Memory Acceleration Using Integer Linear Programming
Liu, J., Zhou, M., Pan, Y., Yang, C.-Y., Josipović, L., & Rosing, T. (2025) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3695053.3731041 · Cited by 11
“We evaluate OptiPIM on several widely used convolutional and transformerneuralnetworks,includingAlexNet[29],ResNet-50[17], ResNet-152 [17], UNet [22], VGG [55], BERT-base [10], and Llama-3 8B and 14B models [14, 50].”
Shelke, N. M., Somkunwar, R. K., Pimpalkar, A. P., et al. (2025) · Automatika · doi:10.1080/00051144.2025.2514884 · Cited by 6
“In 2012, AlexNet [24] surprised the world with its deep learning prowess, dominating the ImageNet challenge.”
Ma, G., Yang, G., Lu, H., & Zhang, X. (2025) · Remote Sensing · doi:10.3390/rs17132179 · Cited by 6
Detection and Geolocation of Peat Fires Using Thermal Infrared Cameras on Drones
Sam-Odusina, T., Perkasa, P., Chalmers, C., Fergus, P., Longmore, S. N., & Wich, S. A. (2025) · Drones · doi:10.3390/drones9070459 · Cited by 10
WSTCNN: A Wavelet Scattering Transform-CNN Model for Wind Speed Estimation From Radar Images
Yang, Z., & Huang, W. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3583575 · Cited by 6
Chen, Z., Zhang, N., Xu, C., Xu, Z., Han, S., & Jiang, L. (2025) · Buildings · doi:10.3390/buildings15132292 · Cited by 9
A deep convolutional neural network-based novel class balancing for imbalance data segmentation
Kalsoom, A., Iftikhar, M. A., Ali, A., Shah, Z., Balakrishnan, S., & Ali, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-04952-y · Cited by 7
“Orlando et al. [24] segmented blood vessels by discriminatively training a fully connected Conditional Random Field (CRF) model.”
Urban change detection of remote sensing images via deep-feature extraction
Wang, H., & Wu, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-07252-7 · Cited by 7
Wang, Q., Kavhiza, N. J., Islam, F., et al. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3584853 · Cited by 6
A survey of computational techniques for fine art painting classification
Rathi, V., Sharma, A., Nithin, A., Singh, A. K., & Gupta, B. B. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105626 · Cited by 9
Sun, X., Huang, L. Q., Qu, L., Chen, C., Zeng, X., Zhou, Z., Li, H., Sun, J., Lang, X., Guo, J. J., et al. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3585552 · Cited by 7
Xia, K., Chang, X.-D., Liu, C.-S., Yan, Y.-H., Sun, H., Wang, Y., & Wang, X. (2025) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-025-01680-2 · Cited by 9
“For sophisticated classification and prediction tasks, distinct deep learning structures such as Convolutional Neural Networks (CNN) [50, 51] and Recurrent Neural Networks (RNN) [52] are developed for spatial and sequential data format respectively.”
Potential role of developmental experience in the emergence of the parvo-magno distinction
Vogelsang, M., Vogelsang, L., Pipa, G., DIAMOND, S. P., & Sinha, P. (2025) · Communications Biology · doi:10.1038/s42003-025-08382-4 · Cited by 7
Sharpness-Aware Minimization method with momentum acceleration for deep neural networks
Kang, H., Jiang, Y., Liu, J., & Xu, D. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113967 · Cited by 6
Sandhu, S. K., & Bhatia, R. (2025) · SN Computer Science · doi:10.1007/s42979-025-04173-0 · Cited by 8
“Feature Extraction: A 4096-dimensional feature vector is extracted from each region proposal using the Caffe [7] implementation of the CNN described by researchers et al in [8].”
Lu, T., Zhou, L., Zhang, N., et al. (2025) · Geophysical Journal International · doi:10.1093/gji/ggaf263 · Cited by 6
Hein, S. P., Schultheiss, M., Gafita, A., Zaum, R., Yagubbayli, F., Tauber, R., Rauscher, I., Eiber, M., Pfeiffer, F., & Weber, W. A. (2025) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-025-07426-5 · Cited by 6
“…(2D, 3D), the Siamese network was created in 2D and 3D. Additionally, the Adam optimizer [29], learning rate scheduling [28, 30, 31 ], ℓ 2 -parameter regularization [ 32 ] and a dropout rate [ 33 ] have been applied as recommended for siamese networks (for details see Supplements: Siamese Network).”
Evolutionary Neural Architecture Search for Remote Sensing Image Classification
Liang, J., Liu, G., Bi, Y., Yu, M., Liu, M., & Jin, Y. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3579517 · Cited by 10
Billi, D., Caroti, G., & Piemonte, A. (2025) · Sensors · doi:10.3390/s25144410 · Cited by 7
Knowledge fusion in deep learning-based medical vision-language models: A review
Xu, D., Chen, Y., Chai, Z., Xiao, Y., Yan, Y., Ding, W., Wang, H., Jin, Z. J., Jiao, W., Yue, W., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103455 · Cited by 6
Implementation of convolutional neural networks for microbial colony recognition
Kong, F., Su, M., Guo, J., Wu, H., Chen, H., Qiu, J., & Huang, J. (2025) · Microbiology Spectrum · doi:10.1128/spectrum.02885-24 · Cited by 10
“In 2012, Krizhevsky et al. (12) proposed a deep neural network called AlexNet.”
Kano, K., Segi, T., Ozono, H., & Koga, K. (2025) · Journal of Power Sources · doi:10.1016/j.jpowsour.2025.237944 · Cited by 7
Song, X., Chen, M., Rao, J., et al. (2025) · Sensors · doi:10.3390/s25154660 · Cited by 6
“Although traditional convolutional neural networks (CNNs) perform well in extracting local features [8], they have difficulty modeling long-distance dependencies [9].”
Global Trends in Artificial Intelligence. Challenges, Opportunities, and Prospects
Zgurovsky, M. Z. (2025) · Cybernetics and Systems Analysis · doi:10.1007/s10559-025-00790-y · Cited by 10
“A major breakthrough came with the AlexNet architecture (2012) [18], which contained 60 million parameters.”
Hsu, K.-C., Wang, P., Su, B., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf392 · Cited by 6
“DL has demonstrated remarkable results across diverse domains, including computer vision and speech recognition [12,13].”
Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection
Li, H., Wang, W., Wang, C., Wang, M., Zhang, X., Lan, L., Liu, X., Li, K., & Cao, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3596089 · Cited by 8
Liu, M., Yi, X.-Y., Chen, Y.-Z., Li, M. H., Zhang, Y.-Y., Zhang, C. J. P., Huang, J., & Ming, W. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100894 · Cited by 6
Surface Defect Detection of Magnetic Tiles Based on YOLOv8-AHF
Ma, C., Pan, Y., & Chen, J. (2025) · Electronics · doi:10.3390/electronics14142857 · Cited by 6
liu, Y., Wu, Y., Xia, Q., et al. (2025) · Journal of Translational Medicine · doi:10.1186/s12967-025-06686-x · Cited by 6
“Deep learning (DL), a subset of ML, has shown exceptional performance in biomedical applications owing to its capacity to process and learn from high-dimensional, multimodal data [19].”
Bai, H., Tong, W., Geng, Z., & Gao, C. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327206 · Cited by 12
“Krizhevsky et al. [6] identified convolutional neural networks (CNNs) as a typical deep learning method capable of enabling end-to-end learning.”
Mi, C., Liu, J., Li, Y., Liu, W., Fang, X., Peng, W., & He, G. (2025) · Theoretical and Applied Fracture Mechanics · doi:10.1016/j.tafmec.2025.105166 · Cited by 6
Landslide detection using deep learning on remotely sensed images
Song, Y., Hao, L., & Li, W. (2025) · Applied Computing and Geosciences · doi:10.1016/j.acags.2025.100278 · Cited by 7
DFCT-net for automatic modulation recognition in UAV communication systems
Shen, Y., Yang, Y., Liu, Y., Wang, N., Ma, L., Wang, H., & Li, F. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131200 · Cited by 8
Neuromorphic Photonic On-Chip Computing
Gupta, S., & Xavier, J. (2025) · Chips · doi:10.3390/chips4030034 · Cited by 10
WB-Former: A Hybrid Model of CNN and Transformer for Water Body Extraction in Complex Scenes
Tian, Y., Cao, H., Liu, Y., et al. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3599510 · Cited by 6
Bi, X., Liu, J., Meng, F., et al. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108448 · Cited by 6
Intelligent analysis of chest X-ray based on multi-modal instruction tuning
Yao, J., Wang, J., Xiao, Z., Hao, X., & Jiang, X. (2025) · Meta-Radiology · doi:10.1016/j.metrad.2025.100172 · Cited by 7
Wang, Y., Sun, H., Jiang, T., Shi, J., Wang, Q., Yang, H., & Qiao, Y. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1635016 · Cited by 6
Hussain, S. S., Xu, D., Shah, P. M., Khan, H., & Zeb, A. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102638 · Cited by 8
Utilizing Detectron2 for accurate and efficient colon cancer detection in histopathological images
Chen, L., Shen, J., Li, X., et al. (2025) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2025.1593534 · Cited by 6
Xie, S., Singer, J., Yilmaz, B., KAISER, D. H., & Cichy, R. M. (2025) · PLoS Biology · doi:10.1371/journal.pbio.3003354 · Cited by 20
“For this, we used representational similarity analysis (RSA) [43,65] to compare representations in the brain and in the layers of an 8-layer AlexNet CNN model trained on object categorization [66,67] (Fig 3A).”
Survey of smartphone-based datasets for indoor localization: A machine learning perspective
Delfa, G. C. L., Prieto, J., Monteleone, S., Rafique, H., Palesi, M., & Patti, D. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101753 · Cited by 9
Peng, M., & Tang, H. (2025) · Communications Engineering · doi:10.1038/s44172-025-00476-5 · Cited by 6
Öztel, İ. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500393 · Cited by 6
Frequency-driven deep learning network for image splicing forgery detection
Liang, E., Zhang, K., Hua, Z., & Jia, X. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114365 · Cited by 6
Ding, L., Jiang, W., Li, Q., et al. (2025) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-025-03079-w · Cited by 6
A Gabor-enhanced deep learning approach with dual-attention for 3D MRI brain tumor segmentation
Chamseddine, E., Tlig, L., Chaâri, L., et al. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111047 · Cited by 6
Domain Generalization for Semantic Segmentation: A Survey
Schwonberg, M., & Gottschalk, H. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00640 · Cited by 12
“Over the last decade, deep neural networks (DNNs) have paved the way for major progress in the field of computer vision [8, 27, 28, 43].”
KD-KI: Knowledge distillation with knowledge infusion for anomaly detection and localization
Huang, W., Xu, Z., Wan, R., Yang, X.-H., & Zhang, B. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131423 · Cited by 8
di Tria, A., Cavicchioli, G., Giannoccaro, P., Morichetti, F., Melloni, A. I., Ferrari, G., Sampietro, M., & Zanetto, F. (2025) · Laser & Photonics Review · doi:10.1002/lpor.202500610 · Cited by 10
Chen, S., Wang, X., Liu, T., et al. (2025) · Ecosystem Services · doi:10.1016/j.ecoser.2025.101778 · Cited by 6
Soni, T. K., & Pujari, P. (2025) · Evolutionary Intelligence · doi:10.1007/s12065-025-01090-2 · Cited by 6
Wu, M., Hu, Y., Tian, F., & Lin, H. (2025) · Technology in Cancer Research & Treatment · doi:10.1177/15330338251380966 · Cited by 7
Bearing fault diagnosis method based on SAGAN and improved ResNet
Wang, G., Shi, N., Yang, X., Liu, Z., & Liu, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-16771-2 · Cited by 8
“At present, convolutional neural networks have achieved superhuman performance in some complex visual tasks 33–36 .”
Traditional Chinese Painting Completion via Hierarchical Optimal Transport
Jiang, W., Zhang, S., You, S., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3615386 · Cited by 6
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
