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 55,501–55,600 of 108,439
Liang, X., Wu, J., & Cao, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03522 · Cited by 9
Mean-field Langevin System, Optimal Control and Deep Neural NetworksPreprint
Hu, K., Kazeykina, A., & Ren, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.07278 · Cited by 14
Attacking Vision-based Perception in End-to-End Autonomous Driving ModelsPreprint
Boloor, A., Garimella, K., He, X. J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.01907 · Cited by 9
Compositional Generalization for Primitive SubstitutionsPreprint
Li, Y., Zhao, L., Wang, J., & Hestness, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.02612 · Cited by 26
SpatialFlow: Bridging All Tasks for Panoptic SegmentationPreprint
Chen, Q., Cheng, A., He, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08787 · Cited by 9
Understanding Architectures Learnt by Cell-based Neural Architecture SearchPreprint
Shu, Y., Wang, W., & Cai, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09569 · Cited by 70
Sanders, J. W., Fletcher, J. R., Frank, S. J., Liu, H., Johnson, J. M., Zhou, Z., Chen, H., Venkatesan, A. M., Kudchadker, R. J., Pagel, M. D., et al. (2019) · SoftwareX · doi:10.1016/j.softx.2019.100347 · Cited by 9
Mozaffari, M. H., Ratul, M. A. R., & Lee, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.03972 · Cited by 9
Influence of stimulus complexity on the specificity of visual perceptual learningPreprint
Bakhtiari, S., Awada, A., & Pack, C. C. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/832303 · Cited by 21
ModelHub.AI: Dissemination Platform for Deep Learning ModelsPreprint
Hosny, A., Schwier, M., Berger, C., Örnek, E. P., Turan, M., Tran, P. V., Weninger, L., Isensee, F., Maier-Hein, K. H., McKinley, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.13218 · Cited by 21
A SOT-MRAM-based Processing-In-Memory Engine for Highly Compressed DNN ImplementationPreprint
Yuan, G., Ma, X., Lin, S., Li, Z., & Ding, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05416 · Cited by 9
Training Deep Learning models with small datasets.Preprint
Romero, M., Interian, Y., Solberg, T. D., et al. (2019) · arXiv (Cornell University) · Cited by 9
Triple Generative Adversarial NetworksPreprint
Li, C., Xu, K., Liu, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09784 · Cited by 9
Emotion Recognition from SpeechPreprint
Venkataramanan, K., & Rajamohan, H. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10458 · Cited by 85
Discovery of Dynamics Using Linear Multistep MethodsPreprint
Keller, R. T., & Du, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.12728 · Cited by 9
Convolutional Networks with Dense ConnectivityPreprint
Huang, G. M., Liu, Z., Pleiss, G., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.02394 · Cited by 9
Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color SpacePreprint
Pestana, C., Akhtar, N., Liu, W., Glance, D., & Mian, A. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00883 · Cited by 12
State-Aware Tracker for Real-Time Video Object SegmentationPreprint
Chen, X., Li, Z., Yuan, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00482 · Cited by 9
AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload RebalancingPreprint
Geng, T., Li, A., Shi, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10834 · Cited by 9
CNN-based approach for glaucoma diagnosis using transfer learning and LBP-based data augmentationPreprint
Maheshwari, S., Kanhangad, V., & Pachori, R. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08013 · Cited by 9
Evaluation Framework For Large-scale Federated LearningPreprint
Liu, L., Zhang, F., Xiao, J., & Wu, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01575 · Cited by 15
Chatterjee, S., Javid, A. M., Sadeghi, M., Kikuta, S., Liu, D., Mitra, P. P., & Skoglund, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07111 · Cited by 9
Bjerge, K., Nielsen, J. B., Sepstrup, M. V., et al. (2020) · Cited by 9
Deep Quaternion Features for Privacy ProtectionPreprint
Zhang, H., Chen, Y.-T., Xiang, L., Ma, H., Shi, J., & Zhang, Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08365 · Cited by 9
Instance Credibility Inference for Few-Shot LearningPreprint
Wang, Y., Xu, C., Liu, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11853 · Cited by 9
MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task LearningPreprint
Gao, Y., Bai, H., Jie, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.14058 · Cited by 9
Temporally Distributed Networks for Fast Video Semantic SegmentationPreprint
Hu, P., Heilbron, F. C., Wang, O., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.01800 · Cited by 9
Analyzing hCov Genome Sequences: Predicting Virulence and MutationPreprint
Sawmya, S., Saha, A., Tasnim, S., Toufikuzzaman, M., Anjum, N., Rafid, A. H. M., Rahman, M. S., & Rahman, M. S. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.06.03.131987 · Cited by 9
Designing and Training of A Dual CNN for Image DenoisingPreprint
Tian, C., Xu, Y. D., Zuo, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03951 · Cited by 9
Learning to Combine: Knowledge Aggregation for Multi-Source Domain AdaptationPreprint
Wang, H., Xu, M., Ni, B., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08801 · Cited by 9
Improving the HardNet DescriptorPreprint
Pultar, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.09699 · Cited by 10
Towards Learning Convolutions from ScratchPreprint
Neyshabur, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13657 · Cited by 46
The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid ParallelismPreprint
Oyama, Y., Maruyama, N., Dryden, N., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12856 · Cited by 9
Transaction-level Model Simulator for Communication-Limited AcceleratorsPreprint
Kim, S., Wang, J., Seo, Y., Lee, S., Park, Y., Park, S., & Park, C. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.14897 · Cited by 11
Growing Efficient Deep Networks by Structured Continuous SparsificationPreprint
Yuan, X., Savarese, P., & Maire, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.15353 · Cited by 36
Large-time asymptotics in deep learningPreprint
Esteve, C., Geshkovski, B., Pighin, D., & Zuazua, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.02491 · Cited by 34
Eerola, T., Kraft, K., Grönberg, O., Lensu, L. T., Suikkanen, S., Seppälä, J., Tamminen, T., Kalviainen, H. A., & Haario, H. (2020) · doi:10.5194/os-2020-62 · Cited by 9
Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship MiningPreprint
Liu, J., Xia, F., Wang, L., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07097 · Cited by 9
Lifelong Graph LearningPreprint
Wang, C., Qiu, Y., Gao, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00647 · Cited by 9
Bidirectional Attention Network for Monocular Depth EstimationPreprint
Aich, S., Vianney, J. M. U., Islam, M. A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00743 · Cited by 9
A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorchPreprint
Riba, E., Mishkin, D., Shi, J., Ponsa, D., Moreno-Noguer, F., & Bradski, G. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.10521 · Cited by 12
Deep learning for time series classificationPreprint
Fawaz, H. I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00567 · Cited by 31
Trustworthy Convolutional Neural Networks: A Gradient Penalized-based ApproachPreprint
Halliwell, N., & Lécué, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14260 · Cited by 9
Deep Reinforcement Learning for Asset Allocation in US EquitiesPreprint
Alonso, M. N. I., & Srivastava, S. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3711487 · Cited by 17
Combining Ensembles and Data Augmentation can Harm your Calibration
Wen, Y., Jerfel, G., Muller, R., Dusenberry, M. W., Snoek, J., Lakshminarayanan, B., & Tran, D. (2020) · arXiv · doi:10.48550/arxiv.2010.09875 · Cited by 27
Maximum Mutation Reinforcement Learning for Scalable ControlPreprint
Suri, K., Shi, X. Q., Plataniotis, K. N., & Lawryshyn, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13690 · Cited by 19
A unified circuit model of attention: Neural and behavioral effectsPreprint
Lindsay, G. W., Rubin, D. B., & Miller, K. D. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2019.12.13.875534 · Cited by 10
Buda, M., Saha, A., Walsh, R., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07995 · Cited by 9
Learning to Communicate and Correct Pose ErrorsPreprint
Vadivelu, N., Ren, M., Tu, J., Wang, J., & Urtasun, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.05289 · Cited by 40
Köhler, M., & Langer, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13602 · Cited by 9
Parallel Training of Deep Networks with Local UpdatesPreprint
Laskin, M., Metz, L., Nabarro, S., Saroufim, M., Noune, B., Luschi, C., Sohl‐Dickstein, J., & Abbeel, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03837 · Cited by 33
Xie, S. M., Kumar, A., Jones, R., Khani, F., Ma, T., & Liang, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04550 · Cited by 38
AutoCaption: Image Captioning with Neural Architecture SearchPreprint
Zhu, X., Wang, N., Guo, L., & Liu, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09742 · Cited by 11
Batch Group NormalizationPreprint
Zhou, X.-Y., Sun, J., Ye, N., Lan, X., Luo, Q., Lai, B., Esperança, P. M., Yang, G., & Li, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02782 · Cited by 15
Improving the Generalization of End-to-End Driving through Procedural GenerationPreprint
Li, Q., Peng, Z., Zhang, Q., Liu, C., & Zhou, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13681 · Cited by 17
Leave Zero Out: Towards a No-Cross-Validation Approach for Model SelectionPreprint
Li, W., Geng, C., & Chen, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13309 · Cited by 10
Zhou, L., Mao, Q., Huang, X., Zhang, F., & Zhang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.04838 · Cited by 9
GST: Group-Sparse Training for Accelerating Deep Reinforcement LearningPreprint
Lee, J., Kim, S., Kim, S.-J., Jo, W., & Yoo, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09650 · Cited by 9
AlphaCrystal: Contact map based crystal structure prediction using deep learningPreprint
Hu, J., Zhao, Y., Li, Q., Song, Y., Dong, R., Yang, W., & Siriwardane, E. M. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.01620 · Cited by 8
Automated Detection of Equine Facial Action UnitsPreprint
Li, Z., Broomé, S., Andersen, P. H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08983 · Cited by 9
STEP: Segmenting and Tracking Every PixelPreprint
Weber, M., Xie, J., Collins, M. D., Zhu, Y., Voigtlaender, P., Adam, H., Green, B., Geiger, A., Leibe, B., Cremers, D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11859 · Cited by 59
Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr MicrocombsPreprint
Tan, M., Xu, M., & Moss, D. (2021) · Preprints.org · doi:10.20944/preprints202102.0549.v1 · Cited by 8
Automatic Extraction of Secrets from the Transistor Jungle using Laser-Assisted Side-Channel AttacksPreprint
Krachenfels, T., Kiyan, T., Tajik, S., & Seifert, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11656 · Cited by 23
LiftPool: Bidirectional ConvNet PoolingPreprint
Zhao, J., & Snoek, C. G. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00996 · Cited by 18
Temporal Contrastive Graph Learning for Video Action Recognition and RetrievalPreprint
Liu, Y., Wang, K., Lan, H., & Lin, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00820 · Cited by 12
Diversifying Sample Generation for Accurate Data-Free QuantizationPreprint
Zhang, X., Qin, H., Ding, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01049 · Cited by 9
Li, H., Park, S., Dara, A. A., Nam, J., Lee, S., Kim, Y., Matsoukas, S., & Sarikaya, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03373 · Cited by 10
Ergen, T., Sahiner, A., Ozturkler, B., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01499 · Cited by 9
Chen, X., Zhao, X., Gong, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11177 · Cited by 9
From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose EstimationPreprint
Li, C., & Lee, G. H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14843 · Cited by 9
MGN-Net: a multi-view graph normalizer for integrating heterogeneous biological network populationsPreprint
Rekik, I., & Gürbüz, M. B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.03895 · Cited by 10
Correspondence Learning for Deep Multi-Modal Recognition and Fraud Detection
Park, J., Kim, M.-H., & Choi, D. (2021) · Electronics · doi:10.3390/electronics10070800 · Cited by 9
SiT: Self-supervised vIsion Transformer
Atito, S., Awais, M., & Kittler, J. (2021) · arXiv · doi:10.48550/arxiv.2104.03602 · Cited by 75
Efficient and Generic 1D Dilated Convolution Layer for Deep LearningPreprint
Chaudhary, N., Misra, S., Kalamkar, D. D., Heinecke, A., Georganas, E., Ziv, B., Adelman, M., & Kaul, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.08002 · Cited by 9
Algorithms, Data, and Platforms: The Diverse Challenges of Governing AIPreprint
Nitzberg, M., & Zysman, J. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3802088 · Cited by 9
Structure Learning and the Parietal CortexPreprint
Summerfield, C., Luyckx, F., & Sheahan, H. (2019) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/zfxj2 · Cited by 8
Deep Learning for Weakly-Supervised Object Detection and Object Localization: A SurveyPreprint
Shao, F., Chen, L., Shao, J., Ji, W., Xiao, S., Lü, Y., Zhuang, Y., & Xiao, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.12694 · Cited by 9
SafeAMC: Adversarial training for robust modulation recognition modelsPreprint
Maroto, J., Bovet, G., & Frossard, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.13746 · Cited by 10
Adversarially Adaptive Normalization for Single Domain GeneralizationPreprint
Fan, X., Wang, Q., Ke, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01899 · Cited by 9
A systematic collection of medical image datasets for deep learning
Li, J., Zhu, G., Hua, C., Feng, M., BasheerBennamoun, Li, P., Lu, X., Song, J., Shen, P., Xu, X., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.12864 · Cited by 61
Progressive Correspondence Pruning by Consensus LearningPreprint
Zhao, C., Ge, Y., Zhu, F., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00591 · Cited by 9
Dog Breed Classification Using CNN
Varghese, S., & Remya, S. (2021) · doi:10.1002/9781119776529.ch10 · Cited by 9
Satellite-based detection of contrails using deep learning
Kulik, L. (2019) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 10
Rahman, M. M. (2021) · doi:10.33915/etd.8309 · Cited by 9
Toward understanding the neural code of the brain
von der Malsburg, C. (2021) · Biological Cybernetics · doi:10.1007/s00422-021-00903-8 · Cited by 10
Rethinking Supervised Pre-training for Better Downstream TransferringPreprint
Feng, Y., Jiang, J., Tang, M., Jin, R., & Gao, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06014 · Cited by 35
DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable RendererPreprint
Chen, W., Litalien, J., Gao, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00140 · Cited by 9
Plumber: Diagnosing and Removing Performance Bottlenecks in Machine Learning Data PipelinesPreprint
Kuchnik, M., Klimovic, A., Šimša, J., Smith, V., & Amvrosiadis, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.04131 · Cited by 19
Salhaoui, M. (2021) · Digital Repository (Polytechnic University of Cartagena) · doi:10.31428/10317/10416 · Cited by 7
Ammonoid Taxonomy with Supervised and Unsupervised Machine Learning AlgorithmsPreprint
Foxon, F. (2021) · doi:10.31233/osf.io/ewkx9 · Cited by 9
An Ensemble Learning and Slice Fusion Strategy for Three-Dimensional Nuclei Instance SegmentationPreprint
Wu, L., Chen, A., Salama, P., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.28.489938 · Cited by 9
Population-based Ensemble Learning with Tree Structures for Classification
Evans, B. (2019) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.17136296 · Cited by 8
Emerging Innovations in the Near Future Using Deep Learning Techniques
Pramod, A., Naicker, H. S., & Tyagi, A. K. (2022) · doi:10.1002/9781119792437.ch10 · Cited by 9
Image Clustering: An Unsupervised Approach to Categorize Visual Data in Social Science ResearchPreprint
Zhang, H., & Peng, Y. (2021) · doi:10.31235/osf.io/mw57x · Cited by 9
Deo, B. S., Pal, M., Panigrahi, P. K., & Pradhan, A. (2022) · medRxiv · doi:10.1101/2022.11.13.22282265 · Cited by 8
Agarwal, S., Arya, K. V., & Meena, Y. K. (2023) · Research Square · doi:10.21203/rs.3.rs-2443352/v1 · Cited by 9
Evolution of MAC Protocols in the Machine Learning Decade: A Comprehensive SurveyPreprint
Hussien, M. (2023) · doi:10.36227/techrxiv.21968219 · Cited by 11
Richter, O., Xing, Y., Marchi, M. D., Nielsen, C., Katsimpris, M., Cattaneo, R., Ren, Y., Hu, Y., Liu, Q., Sheik, S., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.06793 · Cited by 28
Neural Mechanisms of Creative Problem Solving - From Representational Change to Memory FormationPreprint
Becker, M., Sommer, T., & Cabeza, R. E. L. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.13.544774 · Cited by 9
Diagnosing Alzheimer's Disease Levels Using Machine Learning and MRI: A Novel ApproachPreprint
Kiaei, A. A., Bahadori, R., Zadeh, H. M., Boush, M., Abadijou, S., Safaei, D., & Mehdikhani, A. H. (2023) · Preprints.org · doi:10.20944/preprints202306.1184.v1 · Cited by 10
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
