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 68,101–68,200 of 108,435
Huang, L., McKay, G. N., & Durr, N. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13371 · Cited by 5
Xue, M., Yuan, C., He, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13696 · Cited by 5
Data-Dependent Randomized SmoothingPreprint
Alfarra, M., Bibi, A., Torr, P. H. S., & Ghanem, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04351 · Cited by 10
Nag, S. (2020) · doi:10.31219/osf.io/95wge · Cited by 5
Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging StudiesPreprint
Cai, J., Tang, Y., Yan, K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04872 · Cited by 5
Exploring the Interchangeability of CNN Embedding SpacesPreprint
McNeely-White, D. G., Sattelberg, B., Blanchard, N., & Beveridge, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.02323 · Cited by 12
Communication-Efficient Federated Learning with Compensated Overlap-FedAvgPreprint
Zhou, Y., Ye, Q., & Lv, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06706 · Cited by 5
Bi-Classifier Determinacy Maximization for Unsupervised Domain AdaptationPreprint
Li, S., Lv, F., Xie, B., Liu, C. H., Liang, J., & Qin, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06995 · Cited by 5
Beneventano, P., Cheridito, P., Jentzen, A., & von Wurstemberger, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04326 · Cited by 14
Transformer for Image Quality AssessmentPreprint
You, J., & Korhonen, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.01097 · Cited by 5
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized LabelsPreprint
Yun, S., Oh, S. J., Heo, B., Han, D., Choe, J., & Chun, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05022 · Cited by 5
Machine learning with limited dataPreprint
Yao, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.11461 · Cited by 10
A Comprehensive Evaluation Framework for Deep Model RobustnessPreprint
Guo, J. Q., Bao, W., Wang, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09617 · Cited by 5
Self-Adaptive Training: Bridging Supervised and Self-Supervised LearningPreprint
Huang, L., Zhang, C., & Zhang, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.08732 · Cited by 5
Thompson, J. A. F., Bengio, Y., Formisano, E., & Schönwiesner, M. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.01.26.428323 · Cited by 6
Malware Detection Using Frequency Domain-Based Image Visualization and Deep LearningPreprint
Mohammed, T. M., Nataraj, L., Chikkagoudar, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.10578 · Cited by 5
Hessian-Aware Pruning and Optimal Neural Implant
Yu, S., Yao, Z., Gholami, A., Dong, Z., Kim, S., Mahoney, M. W., & Keutzer, K. (2021) · arXiv · doi:10.48550/arxiv.2101.08940 · Cited by 50
Rapid Neural Architecture Search by Learning to Generate Graphs from DatasetsPreprint
Lee, H., Hyung, E., & Hwang, S. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00860 · Cited by 31
When NAS Meets Watermarking: Ownership Verification of DNN Models via Cache Side Channels.Preprint
Lou, X., Guo, S., Zhang, T., Zhang, Y., & Liu, Y. (2021) · arXiv (Cornell University) · Cited by 5
Detecting Localized Adversarial Examples: A Generic Approach using Critical Region AnalysisPreprint
Li, F., Liu, X., Zhang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05241 · Cited by 5
ObjectAug: Object-level Data Augmentation for Semantic Image SegmentationPreprint
Zhang, J., Zhang, Y., & Xu, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00221 · Cited by 5
A Survey on Understanding, Visualizations, and Explanation of Deep Neural NetworksPreprint
Shahroudnejad, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.01792 · Cited by 48
FTSO: Effective NAS via First Topology Second OperatorPreprint
Wang, L., & Chen, L. (2023) · Preprints.org · doi:10.20944/preprints202303.0345.v1 · Cited by 5
Pécot, T., Cuitiño, M. C., Johnson, R. H., Timmers, C., & Leone, G. W. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.01.433386 · Cited by 5
MixSearch: Searching for Domain Generalized Medical Image Segmentation ArchitecturesPreprint
Liu, L., Wen, Z., Liu, S., Zhou, H.-Y., Zhu, H., Xie, W., Shen, L., Ma, K., & Zheng, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.13280 · Cited by 10
Parametric Complexity Bounds for Approximating PDEs with Neural NetworksPreprint
Marwah, T., Lipton, Z. C., & Risteski, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02138 · Cited by 10
Improving Global Adversarial Robustness Generalization With Adversarially Trained GANPreprint
Wang, D., Jin, W., Wu, Y., & Khan, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.04513 · Cited by 8
LQResNet: A Deep Neural Network Architecture for Learning Dynamic ProcessesPreprint
Goyal, P., & Benner, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02249 · Cited by 6
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain AdaptationPreprint
Wei, G., Lan, C., Zeng, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13575 · Cited by 5
A High-order Tuner for Accelerated Learning and ControlPreprint
McDonald, S., Cui, Y., Gaudio, J. E., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12868 · Cited by 5
Quantum Computing Aided Machine Learning Through Quantum State FidelityPreprint
Stein, S. A. (2021) · Preprints.org · doi:10.20944/preprints202103.0583.v1 · Cited by 5
Siamese Natural Language Tracker: Tracking by Natural Language Descriptions with Siamese TrackersPreprint
Feng, Q., Ablavsky, V., Bai, Q., & Sclaroff, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02048 · Cited by 5
Craig, M. M., Pappas, I., Allanson, J. E., Finoia, P., Williams, G. B., Pickard, J. D., Menon, D. K., & Stamatakis, E. A. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.27.436534 · Cited by 3
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object DetectionPreprint
Wang, Z., Li, Y., Ye, G., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16368 · Cited by 5
Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional LearningPreprint
Xie, J., Zheng, Z., Fang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02812 · Cited by 5
Yang, L., Finamore, A., Jun, F., & Rossi, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.03182 · Cited by 5
CoSA: Scheduling by Constrained Optimization for Spatial AcceleratorsPreprint
Huang, Q., Kang, M., Dinh, G., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.01898 · Cited by 5
SGNet: A Super-class Guided Network for Image Classification and Object DetectionPreprint
Li, K., Wang, N. Y., Yang, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12898 · Cited by 5
Huang, N., Liu, J., Zhang, Q., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11539 · Cited by 5
AG-CUResNeSt: A Novel Method for Colon Polyp SegmentationPreprint
Dinh, S., Tran, C. Q., Phan, L. N., Hang, D., Long, D. V., & Nguyen, T. (2021) · arXiv.org · doi:10.48550/arxiv.2105.00402 · Cited by 24
BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-IdentificationPreprint
Hou, R., Chang, H., Ma, B., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.14783 · Cited by 5
How Well Self-Supervised Pre-Training Performs with Streaming Data?Preprint
Hu, D., Lu, Q., Hong, L., Hu, H., Zhang, Y., Li, Z., Shen, A., & Feng, J. (2021) · arXiv (Cornell University) · Cited by 7
Domain-Specific Suppression for Adaptive Object DetectionPreprint
Wang, Y., Zhang, R., Zhang, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03570 · Cited by 5
Becker, M., & Cabeza, R. E. L. (2021) · doi:10.31234/osf.io/vcfwe · Cited by 5
Cause and Effect: Concept-based Explanation of Neural Networks
Zaeem, M. N. (2021) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2021-14608 · Cited by 5
Improving Adversarial Transferability with Gradient RefiningPreprint
Wang, G., Yan, H., Guo, Y., & Wei, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04834 · Cited by 6
Recognition of identity and expressions as integrated processesPreprint
O’Nell, K., Saxe, R. R., & Anzellotti, S. (2019) · doi:10.31234/osf.io/9c2e5 · Cited by 6
Jang, J., Wang, C., Zhang, X., et al. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/191858 · Cited by 5
Audio-visual scene classification: analysis of DCASE 2021 Challenge submissionsPreprint
Wang, S., Heittola, T., Mesaros, A., & Virtanen, T. I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.13675 · Cited by 8
Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?Preprint
Ren, J., Zhou, Z., Chen, Q., & Zhang, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.10719 · Cited by 13
CLCC: Contrastive Learning for Color ConstancyPreprint
Lo, Y.-C., Chang, C.-C., Chiu, H.-C., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.04989 · Cited by 5
Fast Quantum Property Prediction via Deeper 2D and 3D Graph NetworksPreprint
Liu, M., Fu, C., Zhang, X., Wang, L., Xie, Y., Yuan, H., Luo, Y., Zhao, X., Xu, S., & Ji, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08551 · Cited by 13
Analyzing Non-Textual Content Elements to Detect Academic PlagiarismPreprint
Meuschke, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05764 · Cited by 7
Launchpad: A Programming Model for Distributed Machine Learning ResearchPreprint
Yang, F., Barth-Maron, G., Stańczyk, P., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.04516 · Cited by 5
Affective Image Content Analysis: Two Decades Review and New PerspectivesPreprint
Zhao, S., Yao, X., Yang, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.16125 · Cited by 5
Li, H., Li, Y., Zhang, G., et al. (2021) · arXiv (Cornell University) · Cited by 5
Unbalanced Feature Transport for Exemplar-based Image TranslationPreprint
Zhan, F. (2021) · doi:10.31219/osf.io/f6vur · Cited by 5
Recent Deep Semi-supervised Learning Approaches and Related WorksPreprint
Kim, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11528 · Cited by 13
Semi-Supervised Hypothesis Transfer for Source-Free Domain AdaptationPreprint
Ma, N., Bu, J., Lu, L., Wen, J., Zhang, Z., Zhou, S., & Yan, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.06735 · Cited by 5
Carreira-Perpiñán, M. Á., & Idelbayev, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04380 · Cited by 7
Robust Training of Social Media Image Classification Models for Rapid Disaster ResponsePreprint
Alam, F., Alam, T., Imran, M., & Ofli, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.04184 · Cited by 5
Datta, G., Kundu, S., Jaiswal, A., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11979 · Cited by 5
Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRIPreprint
Fernández-Quilez, Á., Eftestøl, T., Goodwin, M., Kjosavik, S. R., & Oppedal, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10806 · Cited by 5
SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)Preprint
Lukas, N., Jiang, E., Li, X., & Kerschbaum, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.04974 · Cited by 6
Web-Based Model for Apparel ClassificationPreprint
Bhimani, H., Kaimaparambil, K., Papan, V., et al. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3367732 · Cited by 5
Cahyawijaya, S. (2021) · arXiv.org · doi:10.14711/thesis-991012980421703412 · Cited by 11
RepNAS: Searching for Efficient Re-parameterizing BlocksPreprint
Zhang, M., Yu, X., Rong, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03508 · Cited by 5
Sparse-MLP: A Fully-MLP Architecture with Conditional Computation.Preprint
Lou, Y., Xue, F., Zheng, Z., et al. (2021) · arXiv (Cornell University) · Cited by 5
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal TransformerPreprint
Li, S. C., Cao, Q., Liu, L., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.12630 · Cited by 5
To tune or not to tune? An Approach for Recommending Important HyperparametersPreprint
Bahmani, M., Shawi, R. E., Potikyan, N., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13066 · Cited by 5
Object Detection Using Convolution Neural NetworksPreprint
Jhinkwan, P., Ingale, V., & Chaturvedi, S. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3422311 · Cited by 5
The New Abnormal: Network Anomalies in the AI Era
Soro, F., Favale, T., Giordano, D., Vassio, L., Houidi, Z. B., & Drago, I. (2021) · Wiley eBooks · doi:10.1002/9781119675525.ch11 · Cited by 6
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image HarmonizationPreprint
Liang, J., Cun, X., Pun, C., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05750 · Cited by 5
Zhou, G., Chen, Y., & Chien, C. (2021) · Research Square · doi:10.21203/rs.3.rs-888104/v1 · Cited by 5
Towards Evaluating the Robustness of Deep Intrusion Detection Models in Adversarial EnvironmentPreprint
Srinivasan, S., Simran, K., Vinayakumar, R., et al. (2020) · doi:10.36227/techrxiv.12151749 · Cited by 5
Integrating Large Circular Kernels into CNNs through Neural Architecture SearchPreprint
He, K., Li, C., Yang, Y., Huang, G. M., & Hopcroft, J. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.02451 · Cited by 9
The Artificial Intelligence behind the winning entry to the 2019 AI Robotic Racing CompetitionPreprint
Wagter, C. D., Paredes-Vallés, F., Sheth, N., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.14985 · Cited by 5
Kaniuth, P., & Hebart, M. N. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.09.27.462005 · Cited by 5
Tutorial on Deep Learning for Human Activity RecognitionPreprint
Bock, M., Hoelzemann, A., Moeller, M., & Laerhoven, K. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06663 · Cited by 6
High-resolution rainfall-runoff modeling using graph neural networkPreprint
Xiang, Z., & Demir, İ. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.10833 · Cited by 22
GradSign: Model Performance Inference with Theoretical InsightsPreprint
Zhang, Z., & Jia, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.08616 · Cited by 22
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesPreprint
Choi, K., Hong, D., Park, N., Kim, Y., & Lee, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02625 · Cited by 41
M2MRF: Many-to-Many Reassembly of Features for Tiny Lesion Segmentation in Fundus ImagesPreprint
Liu, Q., Liu, H., Ke, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00193 · Cited by 5
The application of Artificial Intelligence to Ophthalmology: A bibliometric study (2000-2021)Preprint
Wang, H., Zhou, X., Du, W., et al. (2021) · Preprints.org · doi:10.20944/preprints202111.0080.v1 · Cited by 5
QDCNN: Quantum Dilated Convolutional Neural NetworkPreprint
Chen, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15667 · Cited by 6
Unsupervised Lightweight Single Object Tracking with UHP-SOT++Preprint
Zhou, Z., Fu, H., You, S. O., & Kuo, C. ‐. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.07548 · Cited by 4
End-to-End Learned Image Compression with Quantized Weights and ActivationsPreprint
Sun, H., Yu, L., & Katto, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.09348 · Cited by 11
Romanian Speech Recognition Experiments from the ROBIN ProjectPreprint
Avram, A.-M., Păiș, V., & Tufis, D. I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12028 · Cited by 5
An Image Patch is a Wave: Phase-Aware Vision MLPPreprint
Tang, Y., Han, K., Guo, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12294 · Cited by 5
Deep Auto-encoder with Neural ResponsePreprint
Ran, X., Zhang, J., Ye, Z., Wu, H., Xu, Q., Zhou, H., & Liu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15309 · Cited by 12
Strategies in Jpeg Compression Using Convolutional Neural Network(Cnn)Preprint
Kunwar, S. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3978717 · Cited by 5
EnGAN: Enhancement Generative Adversarial Network in Medical Image SegmentationPreprint
Deng, E., Qin, Z., Chen, D., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-1219874/v1 · Cited by 5
AI-based graptolite identification improves shale gas explorationPreprint
Niu, Z., & Xu, H. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.01.17.476477 · Cited by 5
Guan, Y., Chattopadhyay, A., Subel, A., et al. (2021) · doi:10.31223/x5f61w · Cited by 5
Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to HumansPreprint
Zeman, A. A., Leers, T., & de Beeck, H. O. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.03.21.485240 · Cited by 5
Introduction to Digital Dentistry
da Silva, R. L. B., Kim, J. H., Markarian, R. A., et al. (2022) · doi:10.1002/9781119852025.ch1 · Cited by 5
How reliable is perception?Preprint
Lupyan, G. (2017) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/r7sjj · Cited by 6
Perceptual dissociations among views of objects, scenes, and reachable spacesPreprint
Josephs, E. L., & Konkle, T. (2018) · doi:10.31234/osf.io/gm43c · Cited by 5
Ramesh, N. (2018) · doi:10.31979/etd.8c8x-txe7 · Cited by 5
Bi, Y., Xue, B., & Zhang, M. (2020) · doi:10.26686/wgtn.13158329 · Cited by 5
Metadata
- Authors
- Krizhevsky, A., Sutskever, I., & Hinton, G. E.
- Affiliations
- Google (United States) (US)
- University of Toronto (CA)
- Venue
- Communications of the ACM
- Published
- 2017-05-24
- Volume
- 60
- Issue
- 6
- Pages
- 84-90
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2163605009
- Cited by
- 112,155
- References
- 27
- Citations by year
- 2026: 2710 · 2025: 7710 · 2024: 10211 · 2023: 12267 · 2022: 12280 · 2021: 15497 · 2020: 14538 · 2019: 13976 · 2018: 9999 · 2017: 6661
- FWCI
- 5127.18
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- neural information processing systems
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
