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 64,301–64,400 of 108,435
TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural NetworksPreprint
Liu, X., & Di, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.09855 · Cited by 6
Data-Free Knowledge Amalgamation via Group-Stack Dual-GANPreprint
Ye, J., Ji, Y., Wang, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.09088 · Cited by 6
Savioli, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.02136 · Cited by 11
ModuleNet: Knowledge-inherited Neural Architecture SearchPreprint
Chen, Y., Gao, R., Liu, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05020 · Cited by 6
Yasrab, R., Pound, M. P., French, A. P., & Pridmore, T. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.05.01.073270 · Cited by 6
Hierarchical Predictive Coding Models in a Deep-Learning FrameworkPreprint
Hosseini, M., & Maida, A. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03230 · Cited by 12
Streaming Object Detection for 3-D Point CloudsPreprint
Han, W., Zhang, Z., Caine, B., Yang, B., Sprunk, C., Alsharif, O., Ngiam, J., Vasudevan, V., Shlens, J., & Chen, Z. (2020) · European Conference on Computer Vision · doi:10.48550/arxiv.2005.01864 · Cited by 37
Interaction-Aware Trajectory Prediction of Connected Vehicles using CNN-LSTM NetworksPreprint
Mo, X., Xing, Y., & Lv, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.12134 · Cited by 6
FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal RetrievalPreprint
Gao, D., Jin, L.-B., Chen, B., Qiu, M., Li, P., Wei, Y., Hu, Y., & Wang, H. J. (2020) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.48550/arxiv.2005.09801 · Cited by 176
Conditionally Deep Hybrid Neural Networks Across Edge and CloudPreprint
Long, Y., Chakraborty, I., & Roy, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.10851 · Cited by 4
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass LensPreprint
Yang, Z., Wang, Y., Chen, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.14446 · Cited by 6
Weight Pruning via Adaptive Sparsity LossPreprint
Retsinas, G., Elafrou, A., Goumas, G., & Maragos, P. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02768 · Cited by 13
Communication-Computation Trade-Off in Resource-Constrained Edge InferencePreprint
Shao, J., & Zhang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02166 · Cited by 6
Multi Layer Neural Networks as Replacement for Pooling OperationsPreprint
Fuhl, W., & Kasneci, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06969 · Cited by 38
NINEPINS: Nuclei Instance Segmentation with Point AnnotationsPreprint
Yen, T.-A., Hsu, H. C., Pati, P., Gabrani, M., Foncubierta–Rodríguez, A., & Chung, P. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13556 · Cited by 6
Automatic Target Recognition on Synthetic Aperture Radar Imagery: A SurveyPreprint
Kechagias‐Stamatis, O., & Aouf, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02106 · Cited by 6
An Automatic Computer-Based Method for Fast and Accurate Covid-19 DiagnosisPreprint
Jim, A. A. J., Rafi, I., Chowdhury, M. S., Sikder, N., Mahmud, M. A. P., Rubaiee, S., Masud, M., Bairagi, A. K., Bhakta, K., & Nahid, A.-A. (2020) · medRxiv · doi:10.1101/2020.07.02.20136721 · Cited by 6
Sharp Statistical Guarantees for Adversarially Robust Gaussian ClassificationPreprint
Chen, D., Wei, Y., & Ravikumar, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.16384 · Cited by 14
Usefulness of interpretability methods to explain deep learning based plant stress phenotypingPreprint
Nagasubramanian, K., Singh, A. K., Singh, A., Sarkar, S., & Ganapathysubramanian, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.05729 · Cited by 31
Attentive Graph Neural Networks for Few-Shot LearningPreprint
Cheng, H., Zhou, J. T., Tay, W. P., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06878 · Cited by 6
Attacking and Defending Machine Learning Applications of Public CloudPreprint
Goodman, D., & Xin, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.02076 · Cited by 6
CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge GraphsPreprint
Cashman, D., Xu, S., Das, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02865 · Cited by 6
ESMFL: Efficient and Secure Models for Federated LearningPreprint
Lin, S., Wang, C., Li, H., Deng, J., Wang, Y., & Ding, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.01867 · Cited by 5
Detection Defense Against Adversarial Attacks with Saliency MapPreprint
Ye, D., Chen, C., Liu, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02738 · Cited by 6
Imbalanced Image Classification with Complement Cross EntropyPreprint
Kim, Y., Lee, Y., & Jeon, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02189 · Cited by 6
Grounded Adaptation for Zero-shot Executable Semantic ParsingPreprint
Zhong, V., Lewis, M., Wang, S. I., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07396 · Cited by 6
Domain Generalization via Semi-supervised Meta LearningPreprint
Sharifi-Noghabi, H., Asghari, H., Mehrasa, N., & Ester, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.12658 · Cited by 13
Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change CaptioningPreprint
Shi, X., Yang, X., Gu, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14352 · Cited by 6
Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural NetworksPreprint
Tan, W., Patel, D., & Kozma, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.14456 · Cited by 6
Video Action Understanding: A Tutorial.Preprint
Hutchinson, M., & Gadepally, V. N. (2020) · arXiv (Cornell University) · Cited by 6
Theory-based residual neural networks: A synergy of discrete choice models and deep neural networksPreprint
Wang, S., Mo, B., & Zhao, J. (2020) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2010.11644 · Cited by 6
Suh, S., Kim, J., Lukowicz, P., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.10103 · Cited by 6
Self-Supervised Out-of-Distribution Detection in Brain CT ScansPreprint
Venkatakrishnan, A. R., Kim, S. T., Eisawy, R., Pfister, F., & Navab, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.05428 · Cited by 13
Recursive Inference for Variational AutoencodersPreprint
Kim, M., & Pavlović, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08544 · Cited by 8
Time without clocks: Human time perception based on perceptual classificationPreprint
Roseboom, W., Fountas, Z., Nikiforou, K., Bhowmik, D., Shanahan, M., & Seth, A. K. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/172387 · Cited by 6
Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a SurveyPreprint
Plaat, A., Kosters, W. A., & Preuß, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05598 · Cited by 41
Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep LearningPreprint
Zhu, H., Wang, R., Jin, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.12623 · Cited by 6
Co-mining: Self-Supervised Learning for Sparsely Annotated Object DetectionPreprint
Wang, T., Yang, T., Cao, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01950 · Cited by 6
The universal approximation theorem for complex-valued neural networks.Preprint
Voigtländer, F. (2020) · arXiv (Cornell University) · Cited by 5
Öksüz, C., Urhan, O., & Güllü, M. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09132 · Cited by 6
KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense ReasoningPreprint
Song, D., Ma, S.-Y., Sun, Z., Yang, S., & Liao, L.-J. (2020) · Knowledge-Based Systems · doi:10.48550/arxiv.2012.07000 · Cited by 46
Attention-based Image UpsamplingPreprint
Kundu, S., Mostafa, H., Sridhar, S. N., & Sundaresan, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09904 · Cited by 7
Application-driven Privacy-preserving Data Publishing with Correlated AttributesPreprint
Rezaei, A., Xiao, C., Gao, J., Li, B., & Munir, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.10193 · Cited by 12
The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball MethodsPreprint
Tao, W., Long, S., Wu, G., & Tao, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.07314 · Cited by 8
Self-Supervised Multi-View Learning via Auto-Encoding 3D TransformationsPreprint
Gao, X., Hu, W., & Qi, G.-J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00787 · Cited by 6
Siddique, F., Sakib, S., & Siddique, M. A. B. (2019) · Preprints.org · doi:10.20944/preprints201903.0039.v2 · Cited by 6
Simultaneous Recognition of Horizontal and Vertical Text in Natural ImagesPreprint
Choi, C., Yoon, Y., Lee, J., et al. (2018) · Preprints.org · doi:10.20944/preprints201812.0114.v1 · Cited by 6
Dutta, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00663 · Cited by 18
Model-Based Domain GeneralizationPreprint
Robey, A., Pappas, G. J., & Hassani, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11436 · Cited by 62
AISPEECH-SJTU accent identification system for the Accented English Speech Recognition ChallengePreprint
Huang, H., Xiang, X., Yang, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.09828 · Cited by 6
Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform DomainPreprint
Tian, J., Zhou, J., Li, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.04302 · Cited by 6
TransTailor: Pruning the Pre-trained Model for Improved Transfer LearningPreprint
Liu, B., Cai, Y., Guo, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01542 · Cited by 6
When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning FrameworkPreprint
Huang, Z., Zhang, J., & Shan, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01520 · Cited by 6
Convolutional Normalization: Improving Deep Convolutional Network Robustness and TrainingPreprint
Liu, S., Li, X., Zhai, Y., You, C., Zhu, Z., Fernandez‐Granda, C., & Qu, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00673 · Cited by 16
Dilated SpineNet for Semantic SegmentationPreprint
Rashwan, A. M., Du, X., Yin, X., & Li, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12270 · Cited by 10
Contrastive Reasoning in Neural NetworksPreprint
Prabhushankar, M., & AlRegib, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12329 · Cited by 12
Jo-SRC: A Contrastive Approach for Combating Noisy LabelsPreprint
Yao, Y., Sun, Z., Zhang, C., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13029 · Cited by 6
Deepened Graph Auto-Encoders Help Stabilize and Enhance Link PredictionPreprint
Wu, X., & Cheng, Q. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11414 · Cited by 6
COVID-19 personal protective equipment detection using real-time deep learning methodsPreprint
Khosravipour, S., Taghvaei, E., & Charkari, N. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14878 · Cited by 9
Positive Sample Propagation along the Audio-Visual Event LinePreprint
Zhou, J., Zheng, L., Zhong, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00239 · Cited by 6
Video Classification with FineCoarse Networks.Preprint
Huang, G., & Borş, A. G. (2021) · arXiv (Cornell University) · Cited by 6
Selecting Cover Images for Restaurant Reviews: AI vs. Wisdom of the CrowdPreprint
Khern-am-nuai, W., So, H., Cohen, M. C., & Adulyasak, Y. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3808667 · Cited by 6
KuraNet: Systems of Coupled Oscillators that Learn to SynchronizePreprint
Ricci, M. R., Jung, M., Zhang, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02838 · Cited by 6
Exploring Uncertainty in Deep Learning for Construction of Prediction IntervalsPreprint
Lai, Y., Shi, Y., Han, Y., Shao, Y., Qi, M., & Li, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12953 · Cited by 6
PAFNet: An Efficient Anchor-Free Object Detector GuidancePreprint
Xin, Y., Wang, G., Mao, M., Feng, Y., Dang, Q., Ma, Y., Ding, E., & Han, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.13534 · Cited by 12
Singer, J., Seeliger, K., Kietzmann, T. C., et al. (2021) · doi:10.31234/osf.io/xg2uy · Cited by 6
Towards Compact CNNs via Collaborative CompressionPreprint
Li, Y., Lin, S., Liu, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.11228 · Cited by 6
What Is Considered Complete for Visual Recognition?Preprint
Xie, L., Zhang, X., Wei, L., Chang, J., & Tian, Q. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.13978 · Cited by 6
Horry, M. J., Chakraborty, S., Pradhan, B., Fallahpoor, M., Chegeni, H., & Paul, M. (2021) · doi:10.31224/osf.io/tfqa4 · Cited by 7
Speech Mode Classification using the Fusion of CNNs and LSTM Networks
Vakkantula, P. C. (2020) · doi:10.33915/etd.7845 · Cited by 6
Evaluating State-of-the-Art Classification Models Against Bayes OptimalityPreprint
Theisen, R., Wang, H., Varshney, L. R., Xiong, C., & Socher, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03357 · Cited by 6
ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture SearchPreprint
Zeinali, B., Zhuang, D., & Chang, J. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.12549 · Cited by 7
Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning.Preprint
Hong, J., Wang, H., Wang, Z., & Zhou, J. (2021) · arXiv (Cornell University) · Cited by 8
CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencyPreprint
Jalwana, M. A. A. K., Akhtar, N., Bennamoun, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10649 · Cited by 6
Visual Representation Learning Does Not Generalize Strongly Within the Same DomainPreprint
Schott, L., von Kügelgen, J., Träuble, F., Gehler, P., Russell, C., Bethge, M., Schölkopf, B., Locatello, F., & Brendel, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.08221 · Cited by 41
Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLRPreprint
Nguyen, K., Nguyen, Y., & Le, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00587 · Cited by 8
Deep learning based monocular visual-inertial odometry
Esfahani, M. A. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/152280 · Cited by 6
Why Adversarial Reprogramming Works, When It Fails, and How to Tell the DifferencePreprint
Zheng, Y., Feng, X., Xia, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.11673 · Cited by 6
A review of transfer learning for medical image classificationPreprint
Hee, K. E., Cosa‐Linan, A., Maros, M. E., Santhanam, N., Jannesari, M., & Ganslandt, T. (2021) · Research Square · doi:10.21203/rs.3.rs-844222/v1 · Cited by 6
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationPreprint
Qin, H., Ding, Y., Zhang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.00212 · Cited by 6
FrequentNet : A Novel Interpretable Deep Learning Model for Image ClassificationPreprint
Li, Y., Song, K., Sun, Y., & Zhu, L. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3895462 · Cited by 11
MoEfication: Conditional Computation of Transformer Models for Efficient InferencePreprint
Zhang, Z., Lin, Y., Liu, Z., Li, P., Sun, M., & Zhou, J. (2021) · arXiv (Cornell University) · Cited by 6
Powerpropagation: A sparsity inducing weight reparameterisationPreprint
Schwarz, J., Jayakumar, S. M., Pascanu, R., Latham, P. E., & Teh, Y. W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00296 · Cited by 11
Stochastic Training is Not Necessary for GeneralizationPreprint
Geiping, J., Goldblum, M., Pope, P. E., Moeller, M., & Goldstein, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.14119 · Cited by 41
Xie, N., Norman, T., Grewe, D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.10548 · Cited by 6
Revisiting Latent-Space Interpolation via a Quantitative Evaluation FrameworkPreprint
Lu, M., He, T., Park, C. F., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06421 · Cited by 6
Self-Supervised Learning by Estimating Twin Class DistributionsPreprint
Wang, F., Kong, T., Zhang, R., Liu, H., & Li, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.07402 · Cited by 7
Audio-visual Representation Learning for Anomaly Events Detection in CrowdsPreprint
Gao, J., Gong, M., & Li, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14862 · Cited by 6
Sharpness-aware Quantization for Deep Neural NetworksPreprint
Liu, J., Cai, J., & Zhuang, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12273 · Cited by 29
EQC : Ensembled Quantum Computing for Variational Quantum AlgorithmsPreprint
Stein, S., Ding, Y., Wiebe, N., Peng, B., Kowalski, K., Baker, N., Ang, J., & Li, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.14940 · Cited by 9
Convolutional Neural Network for Text: A Stepwise Working GuidancePreprint
Roy, P. K., & Kumar, A. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3973041 · Cited by 6
Accelerated American Option Pricing with Deep Neural NetworksPreprint
Anderson, D. P., & Ulrych, U. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4000756 · Cited by 6
Multi-Classification of Fundus Diseases Based on DSRA-CNNPreprint
Yang, X.-L., & Yi, S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4010998 · Cited by 6
Generative Adversarial Unsupervised Image Restoration in Hybrid Degradation ScenesPreprint
Tang, F., Zhu, X., Hu, J., Tie, J., Zhou, J., & Fu, Y. (2022) · Preprints.org · doi:10.20944/preprints202202.0159.v1 · Cited by 8
Born, J., & Manica, M. (2022) · arXiv (Cornell University) · doi:10.3929/ethz-b-000609688 · Cited by 6
Hecker, L., Maschke, M., Rupprecht, R., van Elst, L. T., & Kornmeier, J. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.13.488148 · Cited by 7
Neuro-Symbolic Hierarchical Rule InductionPreprint
Glanois, C., Feng, X., Jiang, Z., Weng, P., Zimmer, M., Li, D., & Liu, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.13418 · Cited by 11
COVID-DenseNet: A Deep Learning Architecture to Detect COVID-19 from Chest Radiology ImagesPreprint
Islam, M. M., Hannan, T., Sarker, L., et al. (2022) · Preprints.org · doi:10.20944/preprints202005.0151.v3 · 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
