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 58,101–58,200 of 108,438
Deep Bayesian Active Learning, A Brief Survey on Recent AdvancesPreprint
Mohamadi, S., & Amindavar, H. (2020) · arXiv.org · doi:10.48550/arxiv.2012.08044 · Cited by 21
DSRNA: Differentiable Search of Robust Neural ArchitecturesPreprint
Hosseini, R., Yang, X., & Xie, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06122 · Cited by 8
Transfer Learning for COVID-19 Pneumonia Detection and Classification in Chest X-ray ImagesPreprint
Katsamenis, I., Protopapadakis, E. E., Voulodimos, A. S., et al. (2020) · medRxiv · doi:10.1101/2020.12.14.20248158 · Cited by 8
Camera-aware Proxies for Unsupervised Person Re-IdentificationPreprint
Wang, M., Lai, B., Huang, J., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10674 · Cited by 8
BaPipe: Exploration of Balanced Pipeline Parallelism for DNN TrainingPreprint
Zhao, L., Xu, R., Wang, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.12544 · Cited by 8
Stack-based Buffer Overflow Detection using Recurrent Neural NetworksPreprint
Dahl, W. A., Erdődi, L., & Zennaro, F. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.15116 · Cited by 22
Improving Adversarial Robustness in Weight-quantized Neural NetworksPreprint
Song, C., Fallon, E., & Li, H. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.14965 · Cited by 16
Style Normalization and Restitution for Domain Generalization and AdaptationPreprint
Jin, X., Lan, C., Zeng, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00588 · Cited by 8
Line Segment Detection Using Transformers without EdgesPreprint
Xu, Y., Xu, W., Cheung, D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.01909 · Cited by 8
Deep Joint Source Channel Coding for WirelessImage Transmission with OFDMPreprint
Yang, M., Bian, C., & Kim, H.-S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03909 · Cited by 8
Low-cost and high-performance data augmentation for deep-learning-based skin lesion classificationPreprint
Shen, S., Xu, M., Zhang, F., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.02353 · Cited by 8
Understanding Spectral Graph Neural NetworkPreprint
Chen, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06660 · Cited by 16
Revisiting Hierarchical Approach for Persistent Long-Term Video PredictionPreprint
Lee, W., Jung, W., Zhang, H., Chen, T., Koh, J. Y., Huang, T., Yoon, H.-S., Lee, H., & Hong, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06697 · Cited by 22
Instance Localization for Self-supervised Detection PretrainingPreprint
Yang, C., Wu, Z., Zhou, B., & Lin, S. C.-F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08318 · Cited by 8
Adaptive Consistency Regularization for Semi-Supervised Transfer LearningPreprint
Abuduweili, A., Li, X., Shi, H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02193 · Cited by 8
Use of Transfer Learning and Wavelet Transform for Breast Cancer DetectionPreprint
Rasheed, A., Younis, M. S., Qadir, J., & Bilal, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03602 · Cited by 13
Continental generalization of an AI system for clinical seizure recognitionPreprint
Yang, Y., Truong, N. D., Maher, C., Nikpour, A., & Kavehei, O. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.07.433990 · Cited by 8
Network Quantization with Element-wise Gradient ScalingPreprint
Lee, J., Kim, D., & Ham, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00903 · Cited by 8
Scale-aware Automatic Augmentation for Object DetectionPreprint
Chen, Y., Li, Y., Kong, T., Qi, L., Chu, R., Li, L., & Jia, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.17220 · Cited by 8
Open Domain Generalization with Domain-Augmented Meta-LearningPreprint
Yang, S., Cao, Z., Wang, C., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.03620 · Cited by 8
Podracer architectures for scalable Reinforcement Learning
Hessel, M., Kroiss, M., Clark, A., Kemaev, I., Quan, J., Keck, T., Viola, F., & van Hasselt, H. (2021) · arXiv · doi:10.48550/arxiv.2104.06272 · Cited by 8
Thief, Beware of What Get You There: Towards Understanding Model Extraction AttackPreprint
Zhang, X., Fang, C., & Shi, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.05921 · Cited by 18
Mini-batch graphs for robust image classificationPreprint
Mondal, A. K., Jain, V., & Siddiqi, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03237 · Cited by 8
Artificial Intelligence in Drug Discovery: Applications and TechniquesPreprint
Deng, J., Yang, Z., Ojima, I., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.05386 · Cited by 8
A Unified Joint Maximum Mean Discrepancy for Domain AdaptationPreprint
Wang, W., Li, B., Yang, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09979 · Cited by 8
EfficientNetB3 Architecture for Diabetic Retinopathy Assessment using Fundus ImagesPreprint
Elmoufidi, A., & Amoun, H. (2021) · Research Square · doi:10.21203/rs.3.rs-609899/v1 · Cited by 8
Masters, D. A., Labatie, A., Eaton-Rosen, Z., & Luschi, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03640 · Cited by 16
Cell-average based neural network method for hyperbolic and parabolic partial differential equationsPreprint
Qiu, C., & Yan, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00813 · Cited by 11
MSE Loss with Outlying Label for Imbalanced ClassificationPreprint
Kato, S., & Hotta, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.02393 · Cited by 19
Li, X., Gan, L., Zhan, D., Shao, Y., Li, B., & Song, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11954 · Cited by 10
Bashkirova, D., Hendrycks, D., Kim, D., Mishra, S., Saenko, K., Saito, K., Teterwak, P., & Usman, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.11011 · Cited by 10
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language ModelsPreprint
Liu, Z., Rodríguez-Opazo, C., Teney, D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.04024 · Cited by 8
Deep Convolutional Neural Networks
Zhou, D., & Ju, L. B. (2021) · Wiley eBooks · doi:10.1002/047134608x.w8424 · Cited by 8
Lakshmipriya, B., Jayanthi, K., Pottakkat, B., & Ramkumar, G. (2021) · Wiley eBooks · doi:10.1002/9781119785750.ch3 · Cited by 8
Towards Scalable Verification of RL-Driven SystemsPreprint
Amir, G., Schapira, M., & Katz, G. (2021) · arXiv.org · doi:10.48550/arxiv.2105.11931 · Cited by 4
Vision Transformers For Weeds and Crops Classification Of High Resolution UAV ImagesPreprint
Reedha, R., Dericquebourg, E., Canals, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.02716 · Cited by 8
Ming, L., Han, D., Li, D., et al. (2021) · Research Square · doi:10.21203/rs.3.rs-877144/v1 · Cited by 8
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information TransferPreprint
Chen, H., Wu, C., Xu, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08912 · Cited by 8
Large-Scale Deep Learning Optimizations: A Comprehensive SurveyPreprint
He, X., Xue, F., Ren, X., & You, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00856 · Cited by 25
HyperInverter: Improving StyleGAN Inversion via HypernetworkPreprint
Dinh, T. M., Tran, A. T., Nguyen, R. M. H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.00719 · Cited by 8
N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event CamerasPreprint
Kim, J., Bae, J., Park, G., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.01041 · Cited by 8
MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and VideoPreprint
Zhang, D. J., Li, K., Chen, Y., Wang, Y., Chandra, S., Qiao, Y., Liu, L., & Shou, M. Z. (2021) · arXiv (Cornell University) · Cited by 10
Dizaj, S. B., & Valizadeh, P. (2021) · Research Square · doi:10.21203/rs.3.rs-952669/v1 · Cited by 9
Fast deep learning computer-aided diagnosis of COVID-19 based on digital chest x-ray imagesPreprint
Al–antari, M. A., Hua, C.-H., Lee, S., & Bang, J. (2020) · doi:10.21203/rs.3.rs-36353/v2 · Cited by 8
Deep transfer learning - based automated detection of COVID-19 from lung CT scan slicesPreprint
Ahuja, S., Panigrahi, B. K., Dey, N., et al. (2020) · doi:10.36227/techrxiv.12334265 · Cited by 8
Image Compression Using Neural Networks
Deshmukh, K. R. (2019) · doi:10.31979/etd.h8mt-65ct · Cited by 8
Learning From Human Correction For Data-Centric Deep LearningPreprint
Guo, T. (2022) · doi:10.36227/techrxiv.13647974.v7 · Cited by 9
Comprehensive Review of Deep Reinforcement Learning Methods and Applications in EconomicsPreprint
Mosavi, A. H., Ghamisi, P., Faghan, Y., Duan, P., Ardabili, S., Salwana, E., & Band, S. S. (2020) · doi:10.31224/osf.io/5qfex · Cited by 10
A Novel Proposed CNN-SVM Architecture for ECG Scalograms ClassificationPreprint
Özaltın, Ö., & Yeniay, Ö. (2022) · Research Square · doi:10.21203/rs.3.rs-1364437/v1 · Cited by 8
Artificial Neural Networks for Classification
Vrábel, J., Képeš, E., Pořízka, P., & Kaiser, J. (2022) · Wiley eBooks · doi:10.1002/9781119759614.ch9 · Cited by 9
Kathirgamanathan, A., Patel, A., Khwaja, A. S., Venkatesh, B., & Anpalagan, A. (2022) · doi:10.32920/21408579 · Cited by 8
The 27th International Conference on 3D Web Technology
Mouton, C., Preda, M., & Mouttapa Thouvenin, I. (2022) · doi:10.1145/3564533 · Cited by 8
Deep Learning for Video-Based Person Re-Identification: A SurveyPreprint
Islam, K. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4313788 · Cited by 8
A Comprehensive Review of Deep Learning-based Single Image Super-resolutionPreprint
Bashir, S. M. A., Wang, Y., Khan, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.09351 · Cited by 8
Hierarchical organization of social action features along the lateral visual pathwayPreprint
McMahon, E., Bonner, M., & Işık, L. (2023) · doi:10.31234/osf.io/x3avb · Cited by 8
Guo, Q., Luo, F., Tang, H., & Li, Y. (2023) · Theoretical and Applied Climatology · doi:10.1007/s00704-023-04439-8 · Cited by 8
Computing a human-like reaction time metric from stable recurrent vision modelsPreprint
Goetschalckx, L., Govindarajan, L. N., Ashok, A. K., Ahuja, A., Sheinberg, D. L., & Serre, T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.11582 · Cited by 8
Baniya, A. A., Lee, T.-K., Eklund, P., & Aryal, S. (2023) · Preprints.org · doi:10.20944/preprints202306.1738.v1 · Cited by 8
Modeling time-series with deep networks
Längkvist, M. (2014) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 8
GUANinE v1.0: Benchmark Datasets for Genomic AI Sequence-to-Function ModelsPreprint
Robson, E. S., & Ioannidis, N. M. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.12.562113 · Cited by 9
Deep Neural NewsvendorPreprint
Han, J., Hu, M., & Shen, G. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4582188 · Cited by 10
Sharma, V., & Yakimovich, A. (2024) · Scientific Data · doi:10.1038/s41597-024-03064-y · Cited by 8
Paul, B., Paul, M., & Rub, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4843850 · Cited by 11
Wang, Z., Chetouani, A., & Jennane, R. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4867949 · Cited by 8
Zhang, Z., Wu, Q., Ding, S., et al. (2024) · medRxiv · doi:10.1101/2024.10.09.24315195 · Cited by 8
Automated Design of Agentic Systems
Hu, S., Lu, C., & Clune, J. (2024) · arXiv · doi:10.48550/arxiv.2408.08435 · Cited by 10
“An early example is from computer vision, where hand-designed features like HOG (Dalal & Triggs, 2005) were eventually replaced by learned features from Convolutional Neural Networks (CNNs, Krizhevsky et al. (2012)).”
Oscillation-free Quantization for Low-bit Vision Transformers
Liu, S.-Y., Liu, Z., & Cheng, K.-T. (2023) · arXiv · doi:10.48550/arxiv.2302.02210 · Cited by 8
Study on the Helpfulness of Explainable Artificial Intelligence
Labarta, T., Kulicheva, E., Froelian, R., Geißler, C., Melman, X., & von Klitzing, J. (2024) · Communications in Computer and Information Science · doi:10.1007/978-3-031-63803-9_16 · Cited by 8
“To avoid model-specific biases, two different AI models, AlexNet [22] and VGG16 [38], were selected for classification.”
MethodA Locally Distributed Mobile Computing Framework for DNN based Android Applications
Zhang, J., Chen, S., Liu, B., Ma, Y., & Chen, X. (2018) · Proceedings of the Tenth Asia-Pacific Symposium on Internetware · doi:10.1145/3275219.3275236 · Cited by 7
Can You Hear Me Now? Sensitive Comparisons of Human and Machine Perception
Lepori, M. A., & Firestone, C. (2022) · Cognitive Science · doi:10.1111/cogs.13191 · Cited by 7
Deep learning for plankton and coral classification
Lumini, A., Nanni, L., & Maguolo, G. (2020) · Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) · doi:10.1016/j.aci.2019.11.004 · Cited by 79
Classification Under Human Assistance
De, A., Okati, N., Zarezade, A., & Gomez-Rodriguez, M. (2021) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v35i7.16738 · Cited by 26
Autoencoding sensory substitution
Tóth, V., & Parkkonen, L. (2019) · Unpublished · doi:10.13140/rg.2.2.10576.87048 · Cited by 7
Automated Detection and Categorization of Genital Injuries Using Digital Colposcopy
Fernandes, K., Cardoso, J. S., & Astrup, B. S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-58838-4_28 · Cited by 7
Evaluating performance of AI operators using roofline model
Chen, Z., Zheng, F., Yu, Q., Sun, R., Guo, F., & Chen, Z. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02794-5 · Cited by 6
An Empirical Study on Root Cause Analysis and Prediction of Network Failure Using Deep Learning
Choi, M., Kim, T.-Y., Lee, J. P., & Koh, S. (2021) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc52510.2021.9621097 · Cited by 9
Fine-Tuned Convolutional Neural Networks for Bangladeshi Vehicle Classification
Rahman, M., Rahman, S., & Ayoobkhan, M. U. A. (2022) · International Conference on Innovations in Science, Engineering and Technology (ICISET) · doi:10.1109/iciset54810.2022.9775889 · Cited by 8
A Deep Learning Model with Attention Mechanism for Dental Image Segmentation
Karacan, M. H., & Yücebaş, S. C. (2022) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora55278.2022.9800072 · Cited by 11
Data Augmentation for Bayesian Deep Learning
Wang, Y., Polson, N., & Sokolov, V. (2022) · Bayesian Analysis · doi:10.1214/22-ba1331 · Cited by 12
Feng, H. X., Jin, Y., Laima, S., et al. (2022) · Applied Sciences · doi:10.3390/app12199610 · Cited by 7
Nimbekar, A., Vatti, C. S., Dinesh, Y. V. S., Singh, S., Gupta, T., Chandrapu, R. R., & Acharyya, A. (2022) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc56010.2022.9908073 · Cited by 8
Bounding box regression with balance for harmonious object detection
Wang, C., & Gong, X. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103665 · Cited by 7
L-GAN: landmark-based generative adversarial network for efficient face de-identification
Jang, S.-S., Kim, C.-J., Hwang, S.-Y., Lee, M.-J., & Ha, Y.-G. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04954-x · Cited by 7
Individual identification of dairy cows based on deep learning and feature fusion
Du, Y., Kou, Y., Li, B., Qin, L., & Gao, D. (2022) · Animal Science Journal · doi:10.1111/asj.13789 · Cited by 8
Depth-Adaptive Deep Neural Network Based on Learning Layer Relevance Weights
Alturki, A., Bchir, O., & Ismail, M. M. B. (2022) · Applied Sciences · doi:10.3390/app13010398 · Cited by 7
Linked motion image‐based dynamic hand gesture recognition
Jain, R., Karsh, R. K., & Barbhuiya, A. A. (2023) · Computer Animation and Virtual Worlds · doi:10.1002/cav.2137 · Cited by 7
Recognition of Commercial Vehicle Driving Cycles Based on Multilayer Perceptron Model
Wang, X., Zhao, Y., & Li, W. (2023) · Sustainability · doi:10.3390/su15032644 · Cited by 7
Zhu, Q., Xiong, J., & Peng, L. (2023) · Biotechnology and Genetic Engineering Reviews · doi:10.1080/02648725.2023.2196846 · Cited by 8
Zhu, L., Tian, Z., & Jing, D. (2023) · Environmental Science and Pollution Research · doi:10.1007/s11356-023-26989-0 · Cited by 7
Visual Reasoning: From State to Transformation
Hong, X., Lan, Y., Pang, L., Guo, J., & Cheng, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268093 · Cited by 9
The State of the Art in Machine Learning-Based Digital Forensics
Oladipo, F. O., Ogbuju, E., Samson, A. F., & Musa, A. E. (2020) · International Journal of Computing and Artificial Intelligence · doi:10.33545/27076571.2021.v2.i1a.21 · Cited by 28
A realtime fingerprint liveness detection method for fingerprint authentication systems
Yuan, C., Zhang, Q., Wu, S., & Wu, Q. M. J. (2023) · Advances in computers · doi:10.1016/bs.adcom.2023.04.004 · Cited by 9
SFF-Siam: A New Oracle Bone Rejoining Method Based on Siamese Network
Yuan, J., Chen, S., Weize, G., et al. (2023) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2023.3284000 · Cited by 7
Robust Proxy: Improving Adversarial Robustness by Robust Proxy Learning
Lee, H. J., & Yong, M.-R. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3288672 · Cited by 7
Holanda, R., Monteiro, R. D. P., & Bastos-Filho, C. J. A. (2023) · Technologies · doi:10.3390/technologies11030068 · Cited by 7
Experimental Observations of the Topology of Convolutional Neural Network Activations
Purvine, E., Brown, D., Jefferson, B. A., Joslyn, C., Praggastis, B., Rathore, A., Shapiro, M. R., Wang, B., & Zhou, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26134 · Cited by 12
Reconfigurable FET Approximate Computing-based Accelerator for Deep Learning Applications
Saravanan, R., Bavikadi, S., Rai, S., et al. (2023) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas46773.2023.10181758 · Cited by 7
Prototype Correction via Contrastive Augmentation for Few-Shot Unconstrained Palmprint Recognition
Jing, K., Zhang, X., Zhang, C., et al. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3309458 · Cited by 7
IDA: an improved dual attention module for pollen classification
Le, G., Bao, S., Yang, D., & Duan, K. (2023) · The Visual Computer · doi:10.1007/s00371-023-03075-7 · Cited by 7
TCS-LipNet: Temporal & Channel & Spatial Attention-Based Lip Reading Network
Chen, H., Li, W., Cheng, Z., Liang, X., & Zhang, Q. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44201-8_34 · Cited by 8
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
