The DOI matches its Crossref record, with a small difference in title or year; 31 of the 31 references it cites were found in a registry or an index; 2 of the 14 sources its claims cite were checked for support.
ImageNet classification with deep convolutional neural networks
Open accessAbstract
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
42 Own result · 21 Own interpretation · 7 No basis given · 4 No full text of the sources · 3 Sources not found · 2 Supported · 2 Not checked yet · 1 Own method
Every source the paper cites for this claim was checked and supports it.
In the paper
“This technique reduces complex co adaptations of neurons, since a neuron cannot rely on the presence of particular other neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper states on p. 1 that dropout prevents complex co-adaptations by randomly omitting hidden units, so a hidden unit cannot rely on other hidden units being present. This directly supports the citing sentence. (LLM, conf=0.95)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is, however, a very efficient version of model combination that only costs about a factor of two during training.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper describes dropout as an efficient way to combine many neural-network models (p. 1). In F.6 Training (p. 17), it reports that ImageNet training took roughly four days with dropout versus two days without it, supporting the approximate factor-of-two training cost. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces our top-1 and top-5 error rates by 1.7% and 1.2%, respectively, as compared with a net with half as many kernels in each convolutional layer trained on one GPU.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The size of our network made overfitting a significant problem, even with 1.2 million labeled training examples”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“So these data augmentation schemes are, in effect, computationally free.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 26
- The quote only partly states this claim. 2
Create a free account to see these claims.
Create a free account to see these assumptions.
34 more claims
Create a free account to see all 82 claims and to verify the 3 references still open.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the field of DL, the CNN is the most famous and commonly employed algorithm [30, 71–75].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Deep CNN architectures with 8, even 22 layers [4], [33], can be useful even for CADe problems where the available training datasets are limited.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fully convolutional neural networks (fCNNs) have provided state-of-the-art performance for object classification and image segmentation (1).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first wave saw the emergence of deep learning as the dominant paradigm for analyzing high-dimensional biological data.”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [1]
Experimental — accuracy not yet measured
19 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.5. Overall architecture
“The third convolutional layer has 384 kernels of size 3 × 3 × 256”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,884
Self-citationLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,501
Self-citation(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Self-citationFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Research works printed but not linked: 13
- Berg A., 2010, Large scale visual recognition challenge
- Deng J., 2009, CVPR09
- Krizhevsky A., 2009, Department of Computer Science
- Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript
- Krizhevsky A., 2011, ESANN
- LeCun Y., 1990, Advances in Neural Information Processing Systems
- LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)
- 10.5555/1896300.1896315 · DOI
- Mensink T., 2012, Italy
- 10.5555/3104322.3104425 · DOI
- Rumelhart D.E., 1985, DTIC Document
- 10.5555/938980.939477 · DOI
- Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences
Cited by
Items 68,001–68,100 of 108,435
Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic RelationsPreprint
Tian, Y., Ma, S., Wen, M., Liu, Y., Cheung, S.-C., & Zhang, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03824 · Cited by 4
Data Sanity Check for Deep Learning Systems via Learnt AssertionsPreprint
Lu, H., Xu, H., Liu, N., Zhou, Y., & Wang, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03835 · Cited by 8
Deep Hashing Learning for Visual and Semantic Retrieval of Remote Sensing ImagesPreprint
Song, W., Li, S., & Benediktsson, J. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.04614 · Cited by 5
Adversarial Learning with Margin-based Triplet Embedding RegularizationPreprint
Zhong, Y., & Deng, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09481 · Cited by 5
Shredder: Learning Noise Distributions to Protect Inference PrivacyPreprint
Mireshghallah, F., Taram, M., Ramrakhyani, P., Tullsen, D. M., & Esmaeilzadeh, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11814 · Cited by 9
Convolutional Neural Networks with Dynamic RegularizationPreprint
Wang, Y., Bian, Z.-P., Hou, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11862 · Cited by 5
A Pre-defined Sparse Kernel Based Convolution for Deep CNNsPreprint
Kundu, S., Prakash, S., Akrami, H., Beerel, P. A., & Chugg, K. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00724 · Cited by 5
Hu, J., Li, M., & Gao, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.09003 · Cited by 5
Jafri, S. M. A. H., Hassan, H., Hemani, A., et al. (2019) · arXiv (Cornell University) · doi:10.3929/ethz-b-000463029 · Cited by 5
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual ConvolutionPreprint
Sun, B., Li, J., Shao, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11853 · Cited by 5
CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital ImagesPreprint
Tan, S., Wu, W., Shao, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04657 · Cited by 5
HyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training using TensorFlowPreprint
Awan, A., Jain, A., Anthony, Q., Subramoni, H., & Panda, D. K. (2019) · arXiv.org · doi:10.48550/arxiv.1911.05146 · Cited by 5
Structural Pruning in Deep Neural Networks: A Small-World ApproachPreprint
Krishnan, G., V, Du, X., & Cao, Y. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04453 · Cited by 10
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point NumbersPreprint
Zhang, X., Liu, S., Zhang, R., Liu, C., Huang, D., Zhou, S., Guo, J., Kang, Y., Guo, Q., Du, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00361 · Cited by 8
SoildNet: Soiling Degradation Detection in Autonomous DrivingPreprint
Das, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01054 · Cited by 11
Breaking Medical Data Sharing Boundaries by Employing Artificial RadiographsPreprint
Han, T., Nebelung, S., Haarburger, C., Horst, N., Reinartz, S. D., Merhof, D., Kiessling, F. M., Schulz, V., & Truhn, D. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/841619 · Cited by 5
ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural NetworkPreprint
Li, F., & Yu, H. Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00862 · Cited by 5
Unsupervised Machine Learning for Data Encoding applied to Ovarian Cancer TranscriptomesPreprint
George, T. M., & Lió, P. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/855593 · Cited by 5
Making densenet interpretable a case study in clinical radiologyPreprint
Ngan, K. H., Garcez, A. D., KNAPP, K. M., Appelboam, A., & Reyes‐Aldasoro, C. C. (2019) · medRxiv · doi:10.1101/19013730 · Cited by 5
SparseTrain:Leveraging Dynamic Sparsity in Training DNNs on General-Purpose SIMD ProcessorsPreprint
Gong, Z., Ji, H., Fletcher, C. W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.10175 · Cited by 5
Hybrid Composition with IdleBlock: More Efficient Networks for Image RecognitionPreprint
Xu, B., Tulloch, A., Chen, Y., Yang, X., & Qiao, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.08609 · Cited by 5
Yang, H., Tang, M., Wen, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.09031 · Cited by 5
Simultaneous Region Localization and Hash Coding for Fine-grained Image RetrievalPreprint
Zeng, H., Lai, H., & Yin, J. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.08028 · Cited by 5
End-to-End Learnable Geometric Vision by Backpropagating PnP OptimizationPreprint
Chen, B., Parra, Á., Cao, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06043 · Cited by 5
Discriminative Adversarial Domain AdaptationPreprint
Tang, H., & Jia, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.12036 · Cited by 5
Tan, Y., Elovici, Y., & Binder, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.03609 · Cited by 5
Deep Anomaly Detection in Packet PayloadPreprint
Liu, J., Song, X., Zhou, Y., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02549 · Cited by 5
Kong, Q., Xu, Y., Wang, W., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.04761 · Cited by 5
Precipitation Forecasting via Multi-Scale Deconstructed ConvLSTMPreprint
Xiao, X., Kuang, Q., Xiang, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09425 · Cited by 5
Escaping Saddle Points Faster with Stochastic MomentumPreprint
Wang, J.-K., Lin, C.-H., & Abernethy, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02985 · Cited by 13
Embarrassingly Simple Binary Representation LearningPreprint
Shen, Y., Qin, J., Chen, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.09573 · Cited by 5
Zhou, S., & Schoellig, A. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11511 · Cited by 5
Computations, optimization and tuning of deep feedforward neural networksPreprint
Rahman, M. S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2019.12.27.889311 · Cited by 5
Deep Learning in Multi-organ SegmentationPreprint
Lei, Y., Fu, Y., Wang, T., Qiu, R. L. J., Curran, W. J., Liu, T., & Yang, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.10619 · Cited by 27
Deriving Emotions and Sentiments from Visual Content: A Disaster Analysis Use CasePreprint
Ahmad, K., Zohaib, S., Conci, N., & Al‐Fuqaha, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.03773 · Cited by 3
Lightweight Convolutional Representations for On-Device Natural Language ProcessingPreprint
Desai, S., Goh, G., Babu, A., & Aly, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.01535 · Cited by 6
The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural NetworksPreprint
Luo, X., Roads, B. D., & Love, B. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.02342 · Cited by 5
On the Communication Latency of Wireless Decentralized LearningPreprint
Naderializadeh, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04069 · Cited by 4
Chatarasi, P., Kwon, H., Raina, N., et al. (2020) · arXiv (Cornell University) · Cited by 5
Blind Adversarial Network PerturbationsPreprint
Nasr, M., Bahramali, A., & Houmansadr, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.06495 · Cited by 5
SD-GAN: Structural and Denoising GAN reveals facial parts under occlusionPreprint
Banerjee, S., & Das, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08448 · Cited by 5
The Automated Inspection of Opaque Liquid VaccinesPreprint
Palmer, G., Schnieders, B., Savani, R., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09406 · Cited by 5
Auto-Encoding Twin-Bottleneck HashingPreprint
Shen, Y., Qin, J., Chen, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.11930 · Cited by 5
A Visual Communication Map for Multi-Agent Deep Reinforcement LearningPreprint
Nguyen, N. D., Nguyen, T. T., Creighton, D., & Nahavandi, S. (2020) · arXiv (Cornell University) · doi:10.13140/rg.2.2.13433.62563 · Cited by 7
Mind the Gap: Enlarging the Domain Gap in Open Set Domain AdaptationPreprint
Chang, D., Sain, A., Ma, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03787 · Cited by 5
Wu, C., Wang, M., Li, X., Lu, J., Wang, K., & He, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.02628 · Cited by 11
The Utility of Feature Reuse: Transfer Learning in Data-Starved RegimesPreprint
Shadman, R., Murshed, M. G. S., Verenich, E., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04117 · Cited by 5
End-to-End Learning Local Multi-view Descriptors for 3D Point CloudsPreprint
Li, L., Zhu, S., Fu, H., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.05855 · Cited by 5
Seddiki, K., Saudemont, P., Precioso, F., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.03.24.005975 · Cited by 5
MUXConv: Information Multiplexing in Convolutional Neural NetworksPreprint
Lu, Z., Deb, K., & Boddeti, V. N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13880 · Cited by 5
Learning Longterm Representations for Person Re-Identification Using Radio SignalsPreprint
Fan, L., Li, T., Fang, R., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.01091 · Cited by 5
Universal Adversarial Perturbations Generative Network for Speaker RecognitionPreprint
Li, J., Zhang, X., Jia, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03428 · Cited by 5
CNN depth analysis with different channel inputs for Acoustic Scene ClassificationPreprint
Perez-Castanos, S., Naranjo-Alcazar, J., Zuccarello, P., Cobos, M., & Ferri, F. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.04591 · Cited by 8
Bayesian differential programming for robust systems identification under uncertainty
Perdikaris, P. G. (2020) · doi:10.26226/morressier.5f5f8e69aa777f8ba5bd6168 · Cited by 5
Computation on Sparse Neural Networks: an Inspiration for Future HardwarePreprint
Sun, F., Qin, M., Zhang, T., Liu, L., Chen, Y.-K., & Xie, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11946 · Cited by 4
Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size EstimationPreprint
He, J., Shao, Z., Wright, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13188 · Cited by 5
FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model TrainingPreprint
Lym, S., & Erez, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13027 · Cited by 30
Binarizing MobileNet via Evolution-based SearchingPreprint
Phan, H., Liu, Z., Huynh, D. N., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.06305 · Cited by 5
Unsupervised anomaly detection via deep metric learning with end-to-end optimization
Yilmaz, S. F. (2021) · Bilkent University Institutional Repository (Bilkent University) · Cited by 4
Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot LearningPreprint
Yeh, J.-F., Lee, H.-Y., Tsai, B.-C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.09218 · Cited by 5
Integrating Deep Learning into CAD/CAE System: Case Study on Road Wheel Design Automation.Preprint
Yoo, S., Lee, S., Kim, S., et al. (2020) · arXiv (Cornell University) · Cited by 5
Learning Manifold Patch-Based Representations of Man-Made ShapesPreprint
Smirnov, D., Bessmeltsev, M., & Solomon, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.12337 · Cited by 5
CNN Acceleration by Low-rank Approximation with Quantized FactorsPreprint
Kozyrskiy, N., & Phan, A. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08878 · Cited by 12
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio EstimationPreprint
Kato, M., & Teshima, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06979 · Cited by 6
Collective Learning by Ensembles of Altruistic Diversifying Neural NetworksPreprint
Brazowski, B., & Schneidman, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11671 · Cited by 8
Human-Expert-Level Brain Tumor Detection Using Deep Learning with Data Distillation and AugmentationPreprint
Lu, D., Polomac, N., Gacheva, I., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12285 · Cited by 5
Data Efficient Stagewise Knowledge DistillationPreprint
Kulkarni, A., Panchi, N., Raparthy, S. C., & Chiddarwar, S. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.06786 · Cited by 9
Wang, S., Wang, Q., & Zhao, J. (2018) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1812.04528 · Cited by 10
Deep Image Orientation Angle DetectionPreprint
Maji, S., & Bose, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06709 · Cited by 5
Zhang, L., Nan, X., Huang, E., & Liu, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13525 · Cited by 14
Narayanan, S. S., Ramachandran, A., Aakur, S. N., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12791 · Cited by 5
Deep learning for lithological classification of carbonate rock micro-CT imagesPreprint
dos Anjos, C. E. M., Avila, M. R. V., Vasconcelos, A. G. P., Neta, A. P. M., Medeiros, L. C., Evsukoff, A. G., & Surmas, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.15693 · Cited by 5
Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational AutoencodersPreprint
Wang, Q., & Breckon, T. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.01214 · Cited by 5
Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET SynthesisPreprint
Hu, S., Lei, B., Wang, Y., Feng, Z., Shen, Y., & Wang, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03483 · Cited by 5
AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT DenoisingPreprint
Gu, J., & Ye, J. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05753 · Cited by 5
Tang, J., Han, X., Tan, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05742 · Cited by 5
Utilizing Explainable AI for Quantization and Pruning of Deep Neural NetworksPreprint
Sabih, M., Hannig, F., & Teich, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09072 · Cited by 30
Training Deep Neural Networks Without Batch NormalizationPreprint
Gaur, D., Folz, J., & Dengel, A. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07970 · Cited by 9
Discriminative Cross-Domain Feature Learning for Partial Domain AdaptationPreprint
Jing, T., Shao, M., & Ding, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11360 · Cited by 5
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and ResultsPreprint
Fuoli, D., Huang, Z., Gu, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.06290 · Cited by 5
Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot LearningPreprint
Liu, Y., Zhou, L., Bai, X. P., Gu, L., Harada, T., & Zhou, J. W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07451 · Cited by 4
Improving Robustness and Generality of NLP Models Using Disentangled RepresentationsPreprint
Wu, J., Li, X., Ao, X., Meng, Y., Wu, F. Q., & Li, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09587 · Cited by 13
Tiroidología y Paratiroidología en cirugía de tiroides y paratiroides
Pardal-Refoyo, J. L. (2020) · Revista ORL · doi:10.14201/orl.23624 · Cited by 5
Ray-based classification framework for high-dimensional dataPreprint
Zwolak, J. P., Kalantre, S. S., McJunkin, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00500 · Cited by 5
It may be time to improve the neuron of artificial neural networkPreprint
Liu, G. (2021) · doi:10.36227/techrxiv.12477266.v10 · Cited by 9
M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening from CT ImagingPreprint
Qian, X., Fu, H., Shi, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03201 · Cited by 5
Discussion of using Machine Learning for Safety Purposes in Human Detection
Bexten, S., Saenz, J., Walter, C., et al. (2020) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa46521.2020.9212028 · Cited by 5
Shape-Texture Debiased Neural Network TrainingPreprint
Li, Y., Yu, Q., Tan, M., Mei, J., Tang, P., Shen, W., Yuille, A., & Xie, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05981 · Cited by 79
DEAL: Difficulty-aware Active Learning for Semantic SegmentationPreprint
Xie, S., Feng, Z., Chen, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08705 · Cited by 5
Deep neural network for solving differential equations motivated by Legendre-Galerkin approximationPreprint
Chudomelka, B., Hong, Y., Kim, H. J., & Park, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12975 · Cited by 8
Sabet, A. J. (2021) · Thesis Commons (OSF Preprints) · doi:10.31237/osf.io/6m5f2 · Cited by 5
FLANNEL: Focal Loss Based Neural Network Ensemble for COVID-19 DetectionPreprint
Qiao, Z., Bae, A., Glass, L. M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.16039 · Cited by 5
Self-supervised Representation Learning for Evolutionary Neural Architecture SearchPreprint
Wei, C., Tang, Y., Niu, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.00186 · Cited by 5
Head and gaze tracking of unrestrained marmosetsPreprint
Turesson, H., Conceição, T. B. R., & Ribeiro, S. T. G. (2016) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/079566 · Cited by 5
Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock PredictionPreprint
Rajaa, S., & Sahoo, J. K. (n.d.) · RePEc: Research Papers in Economics · Cited by 5
Liu, Z., Samwel, N., Weissbart, L., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09877 · Cited by 5
Positive-Congruent Training: Towards Regression-Free Model UpdatesPreprint
Yan, S., Xiong, Y., Kundu, K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09161 · Cited by 5
Enhanced Few-shot Learning for Intrusion Detection in Railway Video SurveillancePreprint
Gong, X. F., Chen, X., & Chen, W. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.04254 · Cited by 5
Channel Tiling for Improved Performance and Accuracy of Optical Neural Network AcceleratorsPreprint
Li, S., Miscuglio, M., Sorger, V. J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07391 · Cited by 5
Liu, A., Tang, S., Chen, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01654 · 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
