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 64,201–64,300 of 108,435
Spatial Pyramid Convolutional Neural Network for Social Event Detection in Static ImagePreprint
Rachmadi, R. F., Uchimura, K., & Koutaki, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.04062 · Cited by 6
Recurrent convolutional neural networks: a better model of biological object recognitionPreprint
Spoerer, C. J., McClure, P., & Kriegeskorte, N. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/133330 · Cited by 14
A Cloud-Assisted Mobile Food Recognition System
Pouladzadeh, P. (2017) · uO Research (University of Ottawa) · doi:10.20381/ruor-20328 · Cited by 6
Ternary Residual NetworksPreprint
Kundu, A., Banerjee, K., Mellempudi, N., Mudigere, D., Das, D., Kaul, B., & Dubey, P. (2017) · arXiv.org · doi:10.48550/arxiv.1707.04679 · Cited by 9
Real-time Deep Video DeinterlacingPreprint
Zhu, H., Liu, X., Mao, X., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.00187 · Cited by 6
Recursive Binary Neural Network Learning Model with 2.28b/Weight Storage RequirementPreprint
Guan, T., Zeng, X., & Seok, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.05306 · Cited by 6
Strategies for Conceptual Change in Convolutional Neural NetworksPreprint
Grachten, M., & Cancino-Chacón, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.01634 · Cited by 10
Deep analytics of atomically-resolved images: manifest and latent featuresPreprint
Ziatdinov, M. A., Dyck, O., Maksov, A., Hudak, B. M., Lupini, A. R., Song, J., Snijders, P. C., Vasudevan, R. K., Jesse, S., & Kalinin, S. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05133 · Cited by 10
A case study on scene recognition using an ensemble convolution neural network
Oh, B.-J., & Lee, J. (2018) · International Conference on Advanced Communication Technology · doi:10.23919/icact.2018.8323751 · Cited by 6
Learning Strict Identity Mappings in Deep Residual NetworksPreprint
Yu, X. F., Yu, Z., & Ramalingam, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.01661 · Cited by 6
How deep should be the depth of convolutional neural networks: a backyard dog case studyPreprint
Gorban, A. N., Mirkes, E. M., & Tyukin, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.01516 · Cited by 6
Tokuoka, Y., Yamada, T. G., Hiroi, N. F., Kobayashi, T. J., Yamagata, K., & Funahashi, A. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/324186 · Cited by 13
Infer related genes from large scale gene expression dataset with embeddingPreprint
Choy, C. T., Wong, C. H., & Chan, S. L. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/362848 · Cited by 5
Automatic Music Transcription with Convolutional Neural Networks using Intuitive Filter Shapes
Sleep, J. (2017) · doi:10.15368/theses.2017.95 · Cited by 6
Universal Approximation with Quadratic Deep NetworksPreprint
Fan, F., Xiong, J., & Wang, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.00098 · Cited by 6
TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial NetworksPreprint
Liu, X., Kong, X., Liu, L., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.07582 · Cited by 6
Efficient Semantic Scene Completion Network with Spatial Group ConvolutionPreprint
Zhang, J., Zhao, H., Yao, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05091 · Cited by 6
Neural Network for CVA: Learning Future ValuesPreprint
She, J.-H., & Grecu, D. L. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3288538 · Cited by 9
Currency Recognition Using Deep Learning
Zhang, Q. (2018) · Tuwhera (Auckland University of Technology) · Cited by 7
Detecting The Objects on The Road Using Modular Lightweight NetworkPreprint
Cao, S., Liu, Y., Lasang, P., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.06641 · Cited by 6
Semantically-Aware Attentive Neural Embeddings for Image-based Visual LocalizationPreprint
Seymour, Z., Sikka, K., Chiu, H.-P., Samarasekera, S., & Kumar, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.03402 · Cited by 9
Sankar, V., Kumar, D., Clausi, D. A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04641 · Cited by 6
Music Artist Classification with Convolutional Recurrent Neural NetworksPreprint
Nasrullah, Z., & Zhao, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04555 · Cited by 6
Marchisio, A., Hanif, M. A., Teimoori, M. T., & Shafique, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.01151 · Cited by 8
A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series ForecastingPreprint
Asadi, R., & Regan, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00636 · Cited by 6
Zhu, H., Guo, M., Li, H., Wang, Q., & Robles‐Kelly, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.05672 · Cited by 6
Tong, F. (2018) · Wiley eBooks · doi:10.1002/9781119170174.epcn201 · Cited by 9
Partition Pruning: Parallelization-Aware Pruning for Deep Neural NetworksPreprint
Shahhosseini, S., Albaqsami, A., Jasemi, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11391 · Cited by 6
Recurrent Neural Networks for P300-based BCIPreprint
Tal, O., & Friedman, D. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10798 · Cited by 11
Accelerating Minibatch Stochastic Gradient Descent using Typicality SamplingPreprint
Peng, X., Li, L., & Wang, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.04192 · Cited by 6
Self-Supervised Learning via Conditional Motion PropagationPreprint
Zhan, X., Pan, X., Liu, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11412 · Cited by 6
Road User Detection in VideosPreprint
Perreault, H., Bilodeau, G.-A., Saunier, N., & Gravel, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.12049 · Cited by 7
Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning ProblemPreprint
McDonagh, S., Parisot, S., Zhou, F., Zhang, X., Leonardis, A., Li, Z., & Slabaugh, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11788 · Cited by 6
Data-Free Learning of Student NetworksPreprint
Chen, H., Wang, Y., Xu, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.01186 · Cited by 6
AOGNets: Compositional Grammatical Architectures for Deep LearningPreprint
Li, X., Song, X., & Wu, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.05847 · Cited by 6
Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric LearningPreprint
Yuan, T., Deng, W., Tang, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.02616 · Cited by 6
Discriminative Ridge Machine: A Classifier for High-Dimensional Data or Imbalanced DataPreprint
Peng, C., & Cheng, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.07496 · Cited by 6
Recursive speech separation for unknown number of speakersPreprint
Takahashi, N., Sudarsanam, P., Goswami, N., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03065 · Cited by 6
Bublin, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11546 · Cited by 6
Ma, X., Yuan, G., Lin, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.00136 · Cited by 6
AI Enabling Technologies: A SurveyPreprint
Gadepally, V. N., Goodwin, J. A., Kepner, J., Reuther, A., Reynolds, H. J. D., Samsi, S., Su, J. K., & Martinez, D. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03592 · Cited by 20
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent VariablesPreprint
Xu, Y. H., Wu, B., Shen, F., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04016 · Cited by 6
Seesaw-Net: Convolution Neural Network With Uneven Group ConvolutionPreprint
Zhang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.03672 · Cited by 9
Self-Supervised Visual Place Recognition Learning in Mobile RobotsPreprint
Pillai, S., & Leonard, J. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04453 · Cited by 7
Learning Smooth Representation for Unsupervised Domain AdaptationPreprint
Cai, G., He, L., Zhou, M., Alhumade, H., & Hu, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10748 · Cited by 6
Han, M., Günay, S. Y., Yıldız, İ., Bonato, P., Onal, C. D., Padır, T., Schirner, G., & Erdo{ğ}muş, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.04863 · Cited by 6
AutoGrow: Automatic Layer Growing in Deep Convolutional NetworksPreprint
Wen, W., Yan, F., Chen, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02909 · Cited by 6
Chen, M., Zhou, P., Wu, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01895 · Cited by 6
Liquid Splash Modeling with Neural NetworksPreprint
Um, K., Hu, X., & Thuerey, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.04456 · Cited by 6
CBinfer: Change-Based Inference for Convolutional Neural Networks on Video DataPreprint
Cavigelli, L., Degen, P., & Benini, L. (2017) · arXiv (Cornell University) · doi:10.3929/ethz-b-000219323 · Cited by 9
End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement LearningPreprint
Luo, W., Sun, P., Zhong, F., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03405 · Cited by 6
Who Will Share My Image? Predicting the Content Diffusion Path in Online Social NetworksPreprint
Hu, W., Singh, K. K., Xiao, F., Han, J., Chuah, C., & Lee, Y. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.09275 · Cited by 7
An Experimental Study of Deep Convolutional Features For Iris RecognitionPreprint
Minaee, S., Abdolrashidi, A., & Wang, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01334 · Cited by 6
Vandal (2018) · Digital Repository Service (Northeastern University) · doi:10.17760/d20292847 · Cited by 6
Charniak, E. An Introduction to Deep Learning
Sullivan, B. T. (2019) · Perception · doi:10.1177/0301006619857273 · Cited by 6
Object Detection in Videos by High Quality Object LinkingPreprint
Tang, P., Wang, C., Wang, X., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.09823 · Cited by 6
Accelerating Large-Kernel Convolution Using Summed-Area TablesPreprint
Zhang, L., Halber, M., & Rusinkiewicz, S. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11367 · Cited by 11
Human Extraction and Scene Transition utilizing Mask R-CNNPreprint
Asati, M., Worranitta, K., & Miyachi, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.08884 · Cited by 6
A system of different layers of abstraction for artificial intelligencePreprint
Serb, A., & Prodromakis, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10508 · Cited by 7
Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign RecognitionPreprint
Soufi, N., & Valdenegro-Toro, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12902 · Cited by 6
EMPNet: Neural Localisation and Mapping Using Embedded Memory PointsPreprint
Avraham, G., Zuo, Y., Dharmasiri, T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.13268 · Cited by 6
Refactoring Neural Networks for VerificationPreprint
Shriver, D., Xu, D., Elbaum, S. G., & Dwyer, M. B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08026 · Cited by 7
Dialog State Tracking with Reinforced Data AugmentationPreprint
Yin, Y., Shang, L., Jiang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07795 · Cited by 6
Shamsipour, G., & Pirasteh, S. (2019) · Preprints.org · doi:10.20944/preprints201908.0289.v1 · Cited by 5
MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-LearningPreprint
Mai, Z., Hu, G., Chen, D., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10059 · Cited by 6
Reflective Decoding Network for Image CaptioningPreprint
Ke, L., Pei, W., Li, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11824 · Cited by 6
HarDNet: A Low Memory Traffic NetworkPreprint
Chao, P., Kao, C.-Y., Ruan, Y.-S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00948 · Cited by 6
Faster and Accurate Classification for JPEG2000 Compressed Images in Networked ApplicationsPreprint
Chamain, L. D., & Ding, Z. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05638 · Cited by 6
Visuomotor Understanding for Representation Learning of Driving ScenesPreprint
Lee, S., Kim, J., Oh, T.-H., Jeong, Y., Yoo, D., Lin, S. C.-F., & Kweon, I. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06979 · Cited by 11
Liu, X., Zhang, J., Lin, Y., & Li, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.01546 · Cited by 22
Deep learning for Chemometric and non-translational dataPreprint
Larsen, J. S., & Clemmensen, L. K. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00391 · Cited by 8
Yan, M., Zhao, M., Xu, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.04985 · Cited by 6
CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis ScreeningPreprint
Tang, C., Zhang, W., Li, H., Li, L., Li, Z., Cai, A., Wang, L., Shi, D., & Yan, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.06777 · Cited by 8
Texture Bias Of CNNs Limits Few-Shot Classification PerformancePreprint
Ringer, S., Williams, W., Ash, T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08519 · Cited by 6
Towards a Unified Evaluation of Explanation Methods without Ground TruthPreprint
Zhang, H., Chen, J., Xue, H., & Zhang, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09017 · Cited by 13
A3GAN: An Attribute-aware Attentive Generative Adversarial Network for Face AgingPreprint
Liu, Y., Li, Q., Sun, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.06531 · Cited by 6
Xiang, Z. J., Miller, D. J., Wang, H., & Kesidis, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.07970 · Cited by 6
Castro, M. D. (2019) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.57127 · Cited by 7
Pruning at a Glance: Global Neural Pruning for Model CompressionPreprint
Salama, A., Ostapenko, O., Klein, T., & Nabi, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00200 · Cited by 17
SPARK: Spatial-aware Online Incremental Attack Against Visual TrackingPreprint
Guo, Q., Xie, X., Juefei-Xu, F., Ma, L., Li, Z., Xue, W., Feng, W., & Liu, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08681 · Cited by 6
Towards Precise End-to-end Weakly Supervised Object Detection NetworkPreprint
Yang, K., Li, D., & Dou, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12148 · Cited by 6
Richer priors for infinitely wide multi-layer perceptronsPreprint
Tsuchida, R., Roosta, F., & Gallagher, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12927 · Cited by 6
Zhou, K. Q., Gao, S., Cheng, J. T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12527 · Cited by 6
Learning from Synthetic Dataset for Crop Seed Instance SegmentationPreprint
Toda, Y., Okura, F., Ito, J., et al. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/866921 · Cited by 6
Ma, X., Wu, G., Hwang, S. J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.01181 · Cited by 6
Topology of deep neural networksPreprint
Naitzat, G., Zhitnikov, A., & Lim, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.06093 · Cited by 92
Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth ImagesPreprint
Fooladgar, F., & Kasaei, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11691 · Cited by 40
Fractional Skipping: Towards Finer-Grained Dynamic CNN InferencePreprint
Shen, J., Fu, Y., Wang, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00705 · Cited by 6
Ordered or Orderless: A Revisit for Video based Person Re-IdentificationPreprint
Zhang, L., Shi, Z., Zhou, J. T., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11236 · Cited by 6
Generating Customized Compound Libraries for Drug Discovery with Machine IntelligencePreprint
Moret, M., Friedrich, L., Grisoni, F., et al. (2019) · ChemRxiv · doi:10.26434/chemrxiv.10119299.v1 · Cited by 6
Wide Neural Networks with Bottlenecks are Deep Gaussian ProcessesPreprint
Agrawal, D., Papamarkou, T., & Hinkle, J. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00921 · Cited by 11
Learning with Interpretable Structure from Gated RNNPreprint
Hou, B., & Zhou, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.10708 · Cited by 6
Elastic Consistency: A General Consistency Model for Distributed Stochastic Gradient DescentPreprint
Nadiradze, G., Markov, I., Chatterjee, B., Kungurtsev, V., & Alistarh, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.05918 · Cited by 11
Interpretable Complex-Valued Neural Networks for Privacy ProtectionPreprint
Xiang, L., Ma, H., Zhang, H., Zhang, Y., Ren, J., & Zhang, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09546 · Cited by 22
Temporal Probability CalibrationPreprint
Leathart, T., & Polaczuk, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.02644 · Cited by 9
Post-training Quantization with Multiple Points: Mixed Precision without Mixed PrecisionPreprint
Liu, X., Ye, M., Zhou, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09049 · Cited by 6
Unity Style Transfer for Person Re-IdentificationPreprint
Liu, C., Chang, X., & Shen, Y.-D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.02068 · Cited by 6
PIC: Permutation Invariant Convolution for Recognizing Long-range ActivitiesPreprint
Hussein, N., Gavves, E., & Smeulders, A. W. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08275 · Cited by 13
CoMuTe: A Convolutional Neural Network Based Device Free Multiple Target Localization Using CSIPreprint
Sanam, T. F., & Godrich, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.05734 · Cited by 6
HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud ComputingPreprint
Liu, D., Chen, X., Zhou, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.09876 · 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
