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 53,201–53,300 of 108,439
Factors underlying inter-observer agreement in gaze patterns
Rahman, S., & Bruce, N. D. B. (2016) · doi:10.1145/2857491.2857495 · Cited by 10
Grant, B., Chung, J. H. N., Reiser, I., et al. (2018) · SPIE Medical Imaging: Physics of Medical Imaging · doi:10.1117/12.2292070 · Cited by 10
Schaumberg, A. J., Sirintrapun, S. J., Al‐Ahmadie, H. A., Schüffler, P. J., & Fuchs, T. J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67834-4_4 · Cited by 13
Information-Theoretic Understanding of Population Risk Improvement with Model Compression
Bu, Y., Gao, W., Zou, S., & Veeravalli, V. V. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5730 · Cited by 12
In Defense of the Direct Perception of AffordancesPreprint
Fouhey, D. F., Wang, X., & Gupta, A. K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01085 · Cited by 16
Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural NetsPreprint
Narihira, T., Borth, D., Yu, S. X., Ni, K. S., & Darrell, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06838 · Cited by 11
Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)Preprint
Chernodub, A., & Nowicki, D. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.02313 · Cited by 33
Structured Convolution Matrices for Energy-efficient Deep learningPreprint
Appuswamy, R., Nayak, T. K., Arthur, J. V., Esser, S. K., Merolla, P. A., McKinstry, J. L., Melano, T., Flickner, M., & Modha, D. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.02407 · Cited by 13
Neural Network Architecture Optimization through Submodularity and SupermodularityPreprint
Jin, J., Yan, Z., Fu, K., Jiang, N., & Zhang, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.00074 · Cited by 13
Indexing open imagery to create tools to fight sex trafficking
Stylianou, A., Norling-Ruggles, A., Souvenir, R., et al. (2015) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr.2015.7444535 · Cited by 10
Guest Editorial: Image and Language Understanding
Mitchell, M., Platt, J. C., & Saenko, K. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-0993-y · Cited by 10
Deep Convolutional Decision Jungle for Image ClassificationPreprint
Baek, S., Kim, K. I., & Kim, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.02003 · Cited by 11
Deep transfer learning-based hologram classification for molecular diagnosticsPreprint
Kim, S.-J., Wang, C., Zhao, B., Im, H., Min, J., Choi, H. J., Tadros, J., Choi, N. R., Castro, C. M., Weissleder, R., et al. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/192559 · Cited by 11
Fibernet 2.0: An Automatic Neural Network Based Tool for Clustering White Matter Fibers in the BrainPreprint
Gupta, V., Thomopoulos, S. I., Corbin, C. K., et al. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/210781 · Cited by 10
Adversarial Attacks Beyond the Image SpacePreprint
Zeng, X., Liu, C., Wang, Y.-S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07183 · Cited by 10
Neogi, S. (2020) · doi:10.32657/10356/143222 · Cited by 10
Cuttlefish: A Lightweight Primitive for Adaptive Query ProcessingPreprint
Kaftan, T., Bałazińska, M., Cheung, A., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09180 · Cited by 10
Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICsPreprint
Ding, C., Ren, A., Yuan, G., Ma, X., Li, J., Liu, N., Yuan, B., & Wang, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.11239 · Cited by 11
Kim, H., Kim, S., & Lee, J. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10784 · Cited by 10
Deep ForestPreprint
Zhou, Z., & Feng, J. (2017) · arXiv (Cornell University) · Cited by 10
Taxonomic Classification of Ants (Formicidae) from Images using Deep LearningPreprint
Boer, M. J. A., & Vos, R. A. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/407452 · Cited by 11
BSE: A Minimal Simulation of a Limit-Order-Book Stock ExchangePreprint
Cliff, D. (2018) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1809.06027 · Cited by 10
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree ImagesPreprint
Lee, Y., Jeong, J., Yun, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08196 · Cited by 10
The Taboo Trap: Behavioural Detection of Adversarial SamplesPreprint
Shumailov, I., Zhao, Y., Mullins, R., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.07375 · Cited by 10
Discovering Molecular Functional Groups Using Graph Convolutional Neural NetworksPreprint
Pope, P., Kolouri, S., Rostrami, M., Martin, C. E., & Hoffmann, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00265 · Cited by 23
OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillationPreprint
Ramé, A., Garreau, E., Ben-younes, H., & Ollion, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.02611 · Cited by 20
Layer-Parallel Training of Deep Residual Neural NetworksPreprint
Günther, S., Ruthotto, L., Schroder, J., Cyr, E., & Gauger, N. (2018) · SIAM Journal on Mathematics of Data Science · doi:10.48550/arxiv.1812.04352 · Cited by 108
CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image TransformationPreprint
Babu, K. K., & Dubey, S. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.03554 · Cited by 12
Towards Compact ConvNets via Structure-Sparsity Regularized Filter PruningPreprint
Lin, S., Ji, R., Li, Y., Deng, C. D., & Li, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.07827 · Cited by 16
Ren, H., Su, J., & Lu, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10112 · Cited by 13
Sitatapatra: Blocking the Transfer of Adversarial SamplesPreprint
Shumailov, I., Gao, X., Zhao, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08121 · Cited by 10
Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)Preprint
Gong, S., Shi, Y., & Jain, A. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07327 · Cited by 10
Unsupervised Domain Adaptation Learning Algorithm for RGB-D Staircase RecognitionPreprint
Wang, J., & Zhang, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.01212 · Cited by 13
Real-time PCG Anomaly Detection by Adaptive 1D Convolutional Neural NetworksPreprint
Kıranyaz, S., Zabihi, M., Rad, A. B., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.07238 · Cited by 10
Apple Leaf Disease Identification through Region-of-Interest-Aware Deep Convolutional Neural NetworkPreprint
Yu, H.-J., & Son, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10356 · Cited by 10
Deep Fictitious Play for Stochastic Differential GamesPreprint
Hu, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.09376 · Cited by 10
Neural Architecture Search for Deep Face RecognitionPreprint
Zhu, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.09523 · Cited by 9
Fast and Efficient Zero-Learning Image FusionPreprint
Lahoud, F., & Susstrunk, S. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03590 · Cited by 30
SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud ProcessingPreprint
Kaul, C., Pears, N. E., & Manandhar, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07650 · Cited by 12
End-to-End Wireframe ParsingPreprint
Zhou, Y., Qi, H., & Ma, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03246 · Cited by 10
Automated Steel Bar Counting and Center Localization with Convolutional Neural NetworksPreprint
Fan, Z., Lu, J., Qiu, B., Jiang, T., An, K., Josephraj, A. N., & Wei, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00891 · Cited by 16
A Survey of Behavior Learning Applications in Robotics -- State of the Art and PerspectivesPreprint
Fabisch, A., Petzoldt, C., Otto, M., & Kirchner, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01868 · Cited by 18
Quantifying Layerwise Information Discarding of Neural Networks.Preprint
Ma, H., Zhang, Y., Zhou, F., et al. (2019) · arXiv (Cornell University) · Cited by 10
All-Weather Deep Outdoor Lighting EstimationPreprint
Zhang, J., Sunkavalli, K., Hold-Geoffroy, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.04909 · Cited by 10
Connecting Touch and Vision via Cross-Modal PredictionPreprint
Li, Y., Zhu, J.-Y., Tedrake, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06322 · Cited by 10
Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network EmbeddingsPreprint
Alvi, M., Zisserman, A., & Nellåker, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02169 · Cited by 10
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant LearningPreprint
Sun, W., Jiang, W., Trulls, E., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.02545 · Cited by 10
Liu, H., & Cheng, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.09659 · Cited by 10
Efficient Deep Neural NetworksPreprint
Wu, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08926 · Cited by 12
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge AmalgamationPreprint
Shen, C., Xue, M., Wang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07121 · Cited by 10
Three-dimensional Backbone Network for 3D Object Detection in Traffic ScenesPreprint
Li, X., Guivant, J. E., Kwok, N., Xu, Y. S., Khan, S., & Wu, H. (2019) · arXiv (Cornell University) · doi:10.2139/ssrn.4334485 · Cited by 23
NESTA: Hamming Weight Compression-Based Neural Proc. EnginePreprint
Mirzaeian, A., Homayoun, H., & Sasan, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00700 · Cited by 10
Deep Kernel Learning via Random Fourier FeaturesPreprint
Xie, J., Liu, F., Wang, K., & Huang, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.02660 · Cited by 16
Bit Efficient Quantization for Deep Neural Networks
Nayak, P., Zhang, D., & Chai, S. (2019) · arXiv · doi:10.48550/arxiv.1910.04877 · Cited by 51
Solving Optical Tomography with Deep LearningPreprint
Fan, Y., & Ying, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.04756 · Cited by 10
Dissecting Deep Neural NetworksPreprint
Robinson, H., Rasheed, A., & San, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.03879 · Cited by 18
SegSort: Segmentation by Discriminative Sorting of SegmentsPreprint
Hwang, J.-J., Yu, S. X., Shi, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.06962 · Cited by 10
Best Practices for Convolutional Neural Networks Applied to Object Recognition in ImagesPreprint
de Andrade, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.13029 · Cited by 15
Spontaneous generation of face recognition in untrained deep neural networksPreprint
Baek, S., Song, M. J., Jang, J., Kim, G., & Paik, S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/857466 · Cited by 9
Samarth, C. A. G., Bhowmik, N., & Breckon, T. P. (2019) · arXiv (Cornell University) · Cited by 10
Goyal, M., Knackstedt, T., Yan, S., & Hassanpour, S. (2019) · PubMed Central · doi:10.48550/arxiv.1911.11872 · Cited by 16
A Variational-Sequential Graph Autoencoder for Neural Architecture Performance PredictionPreprint
Friede, D., Lukasik, J., Stuckenschmidt, H., & Keuper, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.05317 · Cited by 12
I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers AdaptivelyPreprint
Wang, H., Chen, T., Wang, Z., & Ma, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10648 · Cited by 12
Liang, K. J., Sigman, J. B., Spell, G. P., Strellis, D. A., Chang, W., Liu, F., Mehta, T. B., & Carin, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.06329 · Cited by 47
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric PriorsPreprint
Tang, L., Chen, K., Wu, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.04803 · Cited by 10
Unsupervised Anomaly Detection for X-Ray ImagesPreprint
Davletshina, D., Melnychuk, V., Tran, V., Singla, H., Berrendorf, M., Faerman, E., Fromm, M., & Schubert, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.10883 · Cited by 32
Deep Frequent Spatial Temporal Learning for Face Anti-SpoofingPreprint
Huang, Y., Zhang, W., & Wang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.03723 · Cited by 10
Deep Affinity Net: Instance Segmentation via AffinityPreprint
Xu, X., Chiu, M. T., Huang, T. S., & Shi, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06849 · Cited by 13
Synthesize then Compare: Detecting Failures and Anomalies for Semantic SegmentationPreprint
Xia, Y., Zhang, Y., Liu, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08440 · Cited by 10
Diversity inducing Information Bottleneck in Model EnsemblesPreprint
Sinha, S., Bharadhwaj, H., Goyal, A., Larochelle, H., Garg, A., & Shkurti, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04514 · Cited by 10
Briot, J.-P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03586 · Cited by 10
Distilling Localization for Self-Supervised Representation LearningPreprint
Zhao, N., Wu, Z., Lau, R. W. H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.06638 · Cited by 10
Where am I looking at? Joint Location and Orientation Estimation by Cross-View MatchingPreprint
Shi, Y., Yu, X. F., Campbell, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.03860 · Cited by 10
Wavelet Integrated CNNs for Noise-Robust Image ClassificationPreprint
Li, Q., Shen, L., Guo, S., & Lai, Z.-H. (2020) · Computer Vision and Pattern Recognition · doi:10.48550/arxiv.2005.03337 · Cited by 268
Konkle, T., & Alvarez, G. A. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.05.28.446118 · Cited by 15
A Deep Neural Network for Audio Classification with a Classifier Attention MechanismPreprint
Lu, H., Zhang, H., & Nayak, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.09815 · Cited by 10
Generalisation Guarantees for Continual Learning with Orthogonal Gradient DescentPreprint
Bennani, M., Doan, T., & Sugiyama, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11942 · Cited by 78
Cyclic Differentiable Architecture SearchPreprint
Yu, H., Peng, H., Huang, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10724 · Cited by 10
On uncertainty estimation in active learning for image segmentationPreprint
Li, B., & Alstrøm, T. (2020) · arXiv.org · doi:10.48550/arxiv.2007.06364 · Cited by 16
Sarma, D., Kavyasree, V., & Bhuyan, M. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08847 · Cited by 14
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image RestorationPreprint
Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., & Dong, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12142 · Cited by 65
One-pixel Signature: Characterizing CNN Models for Backdoor DetectionPreprint
Huang, S., Peng, W., Jia, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07711 · Cited by 10
Optimization of Graph Neural Networks with Natural Gradient DescentPreprint
Izadi, M. R., Fang, Y., Stevenson, R., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09624 · Cited by 10
Huang, X. (2020) · doi:10.5194/gmd-2020-214 · Cited by 10
Residual Learning for Effective joint Demosaicing-DenoisingPreprint
Guo, Y., Jin, Q., Facciolo, G., et al. (2020) · arXiv (Cornell University) · Cited by 10
Wu, J., Li, G., Han, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.08614 · Cited by 10
A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-TimePreprint
Takos, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.12942 · Cited by 23
A Tensor Compiler for Unified Machine Learning Prediction ServingPreprint
Nakandala, S., Saur, K., Yu, G.-I., Karanasos, K., Curino, C., Weimer, M., & Interlandi, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04804 · Cited by 10
How Important is the Train-Validation Split in Meta-Learning?Preprint
Bai, Y., Chen, M., Zhou, P., Zhao, T., Lee, J. D., Kakade, S. M., Wang, H., & Xiong, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05843 · Cited by 28
Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus spacePreprint
Son, G., Walther, D. B., & Mack, M. L. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.10.09.333708 · Cited by 9
BiPointNet: Binary Neural Network for Point CloudsPreprint
Qin, H., Cai, Z., Zhang, M., Ding, Y., Zhao, H., Yi, S., Liu, X., & Su, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05501 · Cited by 50
An SMT-Based Approach for Verifying Binarized Neural Networks
Amir, G. (2021) · doi:10.26226/morressier.604907f41a80aac83ca25cda · Cited by 9
Qi, X., Brown, L., Foran, D. J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03585 · Cited by 10
Towards Good Practices in Self-supervised Representation LearningPreprint
Appalaraju, S., Zhu, Y., Xie, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00868 · Cited by 10
Robust Processing-In-Memory Neural Networks via Noise-Aware NormalizationPreprint
Tsai, L.-H., Chang, S.-C., Chen, Y., Pan, J.-Y., Wei, W., & Juan, D.-C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03230 · Cited by 12
Improving Calibration for Long-Tailed RecognitionPreprint
Zhong, Z., Cui, J., Liu, S., & Jia, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00466 · Cited by 10
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised LearningPreprint
Wang, Z., Jiang, J., Han, B., Feng, L., An, B., Niu, G., & Long, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00925 · Cited by 15
Rethinking FUN: Frequency-Domain Utilization NetworksPreprint
Goldberg, K., Shapiro, S., Richardson, E., & Avidan, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03357 · Cited by 11
MRI Images, Brain Lesions and Deep LearningPreprint
Castillo, D., Lakshminarayanan, V., & Rodríguez-Álvarez, M. J. (2021) · Preprints.org · doi:10.20944/preprints202101.0426.v1 · Cited by 10
Memory Optimization for Deep NetworksPreprint
Shah, A., Wu, C.-Y., Mohan, J., Chidambaram, V., V, & Krähenbühl, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.14501 · Cited by 17
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
