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 67,901–68,000 of 108,435
Active deep learning reduces annotation burden in automatic cell segmentationPreprint
Chowdhury, A., Biswas, S. K., & Bianco, S. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/211060 · Cited by 5
Server, server in the cloud. Who is the fairest in the crowd?Preprint
Böhlen, M., Chandola, V., & Salunkhe, A. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08801 · Cited by 5
Compact Hash Code Learning with Binary Deep Neural NetworkPreprint
Do, T.-T., Hoang, T., Tan, D.-K. L., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.02956 · Cited by 5
Representations of Sound in Deep Learning of Audio Features from MusicPreprint
Shuvaev, S. A., Giaffar, H., & Koulakov, A. A. (2017) · Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory) · doi:10.48550/arxiv.1712.02898 · Cited by 5
Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks
Zhang, F., & Wah, B. W.-S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.466 · Cited by 4
Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network CompilerPreprint
Ji, Y., Zhang, Y., Chen, W., & Xie, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.00746 · Cited by 5
Learning Semantic Segmentation with Diverse SupervisionPreprint
Ye, L., Liu, Z., & Wang, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.00509 · Cited by 5
Build a Compact Binary Neural Network through Bit-level Sensitivity and Data PruningPreprint
Li, Y., & Ren, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.00904 · Cited by 5
Emotion Detection from TextPreprint
Gupta, U., Chatterjee, A., Srikanth, R., & Agrawal, P. (2017) · arXiv (Cornell University) · Cited by 6
Mixed Supervised Object Detection with Robust Objectness TransferPreprint
Li, Y., Zhang, J., Huang, K., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09778 · Cited by 5
Structured Label Inference for Visual UnderstandingPreprint
Nauata, N., Hu, H., Zhou, G.-T., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06459 · Cited by 5
HWNet v2: An Efficient Word Image Representation for Handwritten DocumentsPreprint
Krishnan, P., & Jawahar, C. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06194 · Cited by 5
Active Learning for Breast Cancer IdentificationPreprint
Xie, X., Li, Y., & Shen, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.06670 · Cited by 7
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization BoundsPreprint
Baykal, C., Liebenwein, L., Gilitschenski, I., Feldman, D., & Rus, D. L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.05345 · Cited by 56
Adaptive Selection of Deep Learning Models on Embedded SystemsPreprint
Taylor, B., Marco, V. S., Wolff, W., Elkhatib, Y., & Wang, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.04252 · Cited by 6
Deep Loopy Neural Network Model for Graph Structured Data Representation LearningPreprint
Zhang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07504 · Cited by 5
Monocular Depth Estimation with Augmented Ordinal Depth RelationshipsPreprint
Cao, Y., Zhao, T., Xian, K., Shen, C., Cao, Z., & Xu, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.00585 · Cited by 5
Automated proof synthesis for propositional logic with deep neural networksPreprint
Sekiyama, T., & Suenaga, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11799 · Cited by 7
Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?Preprint
Xu, J., An, W., Zhang, L., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.04329 · Cited by 5
Reversed Active Learning based Atrous DenseNet for Pathological Image ClassificationPreprint
Li, Y., Xie, X., Shen, L., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.02420 · Cited by 5
Do Better ImageNet Models Transfer Better... for Image Recommendation?Preprint
del-Rio, F., Messina, P., Dominguez, V., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.09870 · Cited by 5
Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAVPreprint
Wang, X., Cheng, P., Liu, X., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.05756 · Cited by 5
Spectrum concentration in deep residual learning: a free probability approachPreprint
Ling, Z., He, X., & Qiu, R. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.11694 · Cited by 5
Rethink ReLU to Training Better CNNsPreprint
Zhao, G., Zhang, Z., Guan, H., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.06247 · Cited by 5
Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous DrivingPreprint
Shan, Y., Lu, W. F., & Chew, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.00345 · Cited by 5
American Sign Language fingerspelling recognition in the wildPreprint
Shi, B., Rio, A. M. D., Keane, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.11438 · Cited by 5
NEUZZ: Efficient Fuzzing with Neural Program SmoothingPreprint
She, D., Pei, K., Epstein, D., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.05620 · Cited by 5
Orthogonality of Diffractive Deep Neural NetworksPreprint
Zheng, S., Zeng, X., Zha, L., Shangguan, H., Xu, S., & Fan, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03370 · Cited by 6
Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time SeriesPreprint
Zhang, Q., Luo, R., Yang, Y., & Liu, Y. (2018) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1811.03711 · Cited by 12
Drop-Activation: Implicit Parameter Reduction and Harmonic RegularizationPreprint
Liang, S., Khoo, Y., & Yang, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.05850 · Cited by 5
Deep RNN Framework for Visual Sequential ApplicationsPreprint
Pang, B., Zha, K., Cao, H., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.09961 · Cited by 5
Robust RGB-D Face Recognition Using Attribute-Aware LossPreprint
Jiang, L., Zhang, J., & Deng, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.09847 · Cited by 5
Weakly Supervised Estimation of Shadow Confidence Maps in Fetal Ultrasound ImagingPreprint
Meng, Q., Sinclair, M. D., Zimmer, V. A., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08164 · Cited by 5
Building Efficient Deep Neural Networks with Unitary Group ConvolutionsPreprint
Zhao, R., Hu, Y., Dotzel, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07755 · Cited by 5
Deep Regionlets: Blended Representation and Deep Learning for Generic Object DetectionPreprint
Xu, H., Lv, X., Wang, X., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11318 · Cited by 5
Elastic Boundary Projection for 3D Medical Image SegmentationPreprint
Ni, T., Xie, L., Zheng, H., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00518 · Cited by 5
Dinh, T., & Xin, J. X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.05719 · Cited by 5
Wang, N., Li, C., Huang, X., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04912 · Cited by 5
Classifier and Exemplar Synthesis for Zero-Shot LearningPreprint
Changpinyo, S., Chao, W., Gong, B., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.06423 · Cited by 5
ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of LearningPreprint
Falahati, H., Lotfi-Kamran, P., Sadrosadati, M., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11473 · Cited by 5
Channel Locality Block: A Variant of Squeeze-and-ExcitationPreprint
Li, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01493 · Cited by 5
Deep Semantic Multimodal Hashing Network for Scalable Multimedia Retrieval.Preprint
Jin, L., Tang, J., Li, Z., Qi, G.-J., & Xiao, F. (2019) · arXiv (Cornell University) · Cited by 4
Chou, C.-A., Jin, X., Mueller, A. V., & Ostadabbas, S. (2019) · IEEE Sensors Letters · doi:10.1109/lsens.2018.2886544 · Cited by 5
Neural Network for NILM Based on Operational State Change ClassificationPreprint
Xiao, P., & Cheng, S. S. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02675 · Cited by 8
Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding WindowsPreprint
Yang, Z., Yang, H., Hu, Y., Huang, Y., & Zhang, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.01286 · Cited by 3
Karimian, N., Tehranipoor, F., Anagnostopoulos, N. A., & Yan, W. Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09094 · Cited by 8
Adaptive Cross-Modal Few-Shot LearningPreprint
Chen, X., Rostamzadeh, N., Oreshkin, B. N., & Pinheiro, P. O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07104 · Cited by 191
Compressing complex convolutional neural network based on an improved deep compression algorithmPreprint
Wu, J., Ren, H., Kong, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02358 · Cited by 5
Qi, G.-J., Zhang, L., Chen, C. W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10863 · Cited by 5
Improving image classifiers for small datasets by learning rate adaptationsPreprint
Mishra, S., Yamasaki, T., & Imaizumi, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10726 · Cited by 5
A geometry-inspired decision-based attackPreprint
Liu, Y., Moosavi-Dezfooli, S.-M., & Frossard, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10826 · Cited by 5
OSVNet: Convolutional Siamese Network for Writer Independent Online Signature VerificationPreprint
Sekhar, C., Mukherjee, P., Guru, D. S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00240 · Cited by 5
Interpreting Adversarial Examples with AttributesPreprint
Gulshad, S., Metzen, J. H., Smeulders, A. W. M., & Akata, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08279 · Cited by 5
A Novel BiLevel Paradigm for Image-to-Image TranslationPreprint
Ma, L., Sun, Q., Schiele, B., & Gool, L. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.09028 · Cited by 6
Image Resizing by Reconstruction from Deep FeaturesPreprint
Arar, M., Danon, D., Cohen‐Or, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08475 · Cited by 5
End-to-End Spoken Language TranslationPreprint
Guo, M., Haque, A., & Verma, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.10760 · Cited by 7
Fan, L., Ng, K., & Chan, C. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04368 · Cited by 5
Network Pruning for Low-Rank Binary IndexingPreprint
Lee, D., Kwon, S. J., Kim, B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.05686 · Cited by 5
Modelling urban networks using Variational AutoencodersPreprint
Kempinska, K., & Murcio, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.06465 · Cited by 5
U-Net Based Multi-instance Video Object SegmentationPreprint
Liu, H., & Jiang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07826 · Cited by 6
Local Label Propagation for Large-Scale Semi-Supervised LearningPreprint
Zhuang, C., Ding, X., Murli, D., & Yamins, D. L. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11581 · Cited by 11
A Simple Saliency Method That Passes the Sanity ChecksPreprint
Gupta, A., & Arora, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12152 · Cited by 5
Sketch2code: Generating a website from a paper mockup
Robinson, A. (2019) · arXiv · doi:10.48550/arxiv.1905.13750 · Cited by 18
Don't Paint It Black: White-Box Explanations for Deep Learning in Computer Security.Preprint
Warnecke, A., Arp, D. J., Wressnegger, C., & Rieck, K. (2019) · arXiv (Cornell University) · Cited by 6
A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical ImagingPreprint
Gao, F., Yoon, H., Wu, T. Q., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01828 · Cited by 5
SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized TrainingPreprint
Elthakeb, A. T., Pilligundla, P., & Esmaeilzadeh, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01416 · Cited by 9
Wavelet based edge feature enhancement for convolutional neural networksPreprint
Silva, D. D. N. D., Fernando, S., Piyatilake, I. T. S., & Karunarathne, A. W. S. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.00982 · Cited by 6
Sionnx: Automatic Unit Test Generator for ONNX ConformancePreprint
Cai, X., Zhou, P., Ding, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05676 · Cited by 5
Deep learning in bioinformatics: introduction, application, and perspective in big data eraPreprint
Li, Y., Huang, C., Ding, L., Li, Z., Pan, Y., & Gao, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00342 · Cited by 5
Deep Learning in Robotics: A Review of Recent ResearchPreprint
Pierson, H. A., & Gashler, M. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.07217 · Cited by 6
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDRPreprint
Chen, P., Liao, B., Chen, G., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05509 · Cited by 5
Nakisa, B. (2019) · Queensland University of Technology · doi:10.5204/thesis.eprints.129875 · Cited by 5
The Impact of GPU DVFS on the Energy and Performance of Deep Learning: an Empirical StudyPreprint
Tang, Z., Wang, Y., Wang, Q., & Chu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11012 · Cited by 8
Sparsely Aggregated Convolutional NetworksPreprint
Zhu, L., Deng, R., Maire, M., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05895 · Cited by 5
Towards Optimal Discrete Online Hashing with Balanced SimilarityPreprint
Lin, M., Ji, R., Liu, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10185 · Cited by 5
Deep Learning in the Automotive Industry: Recent Advances and Application ExamplesPreprint
Singh, K. B., & Arat, M. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.08834 · Cited by 25
Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time AppsPreprint
Sehgal, A., & Kehtarnavaz, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.02144 · Cited by 5
A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural NetworksPreprint
Li, Y., Liu, Z., Xu, K., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.06392 · Cited by 5
Zhang, L. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11912 · Cited by 5
Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative FilteringPreprint
Du, X., He, X., Yuan, F., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11171 · Cited by 5
A Preliminary Study on Data Augmentation of Deep Learning for Image ClassificationPreprint
Hu, B., Lei, C., Wang, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11887 · Cited by 5
Guiding High-Performance SAT Solvers with Unsat-Core PredictionsPreprint
Selsam, D., & Bjørner, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.04671 · Cited by 18
A Regularized Convolutional Neural Network for Semantic Image SegmentationPreprint
Jia, F., Liu, J., & Tai, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05287 · Cited by 5
SCOPE: Scalable Composite Optimization for Learning on SparkPreprint
Zhao, S.-Y., Xiang, R., Shi, Y.-H., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.00133 · Cited by 5
Real-World Font Recognition Using Deep Network and Domain AdaptationPreprint
Wang, Z., Yan, S., Jin, H., Shechtman, E., Agarwala, A., Brandt, J., & Huang, T. S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.00028 · Cited by 4
Dubey, K., Agarwal, A., Lathe, A. S., Kumar, R. R., & Srivastava, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10370 · Cited by 5
Dynamic Scale Inference by Entropy MinimizationPreprint
Wang, D., Shelhamer, E., Olshausen, B. A., & Darrell, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03182 · Cited by 5
Banga, D., & Waiganjo, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.02170 · Cited by 5
Deep Cross-Modal Hashing with Hashing Functions and Unified Hash Codes Jointly LearningPreprint
Tu, R.-C., Mao, X.-L., Ma, B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12490 · Cited by 5
Exploiting Channel Similarity for Accelerating Deep Convolutional Neural NetworksPreprint
Zhang, Y., Zhao, C., Ni, B., Zhang, J., & Deng, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.02620 · Cited by 4
Wang, B., Xue, B., & Zhang, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12659 · Cited by 5
On the Robustness of Human Pose EstimationPreprint
Shah, S., Jain, N., Sharma, A., & Jain, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.06401 · Cited by 16
Non-negative Sparse and Collaborative Representation for Pattern ClassificationPreprint
Xu, J., Zhou, X., An, W., Wang, H., & Zhang, D. D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07956 · Cited by 4
Engineering problems in machine learning systemsPreprint
Kuwajima, H., Yasuoka, H., & Nakae, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00001 · Cited by 5
Unsupervised Deep Feature Transfer for Low Resolution Image ClassificationPreprint
Wu, Y., Zhang, Z., & Wang, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10012 · Cited by 5
End-to-End Conditional GAN-based Architectures for Image ColourisationPreprint
Górriz, M., Mrak, M., Smeaton, A. F., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.09873 · Cited by 5
A Possible Reason for why Data-Driven Beats Theory-Driven Computer VisionPreprint
Tsotsos, J. K., Kotseruba, I., Andreopoulos, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10933 · Cited by 5
Chaussonnet, G., Lieber, C., Yikang, Y., et al. (2019) · arXiv (Cornell University) · doi:10.5445/ir/1000097897/v3 · Cited by 5
High-Fidelity State-of-Charge Estimation of Li-Ion Batteries Using Machine LearningPreprint
Wang, W., Brady, N. W., Liao, C., Fahmy, Y., Chemali, E., West, A. C., & Preindl, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02448 · 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
