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 64,501–64,600 of 108,435
Regional gradient pattern (RGP): A novel invariant texture descriptor
Wang, X., Xu, Y., & Niu, P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127215 · Cited by 5
Sheng, D., Jin, W., Wang, M., & Yang, J. (2025) · IEEE Access · doi:10.1109/access.2025.3550895 · Cited by 5
The Prediction of CO2 Plume Using Neural Network Based On the Swin Transformer
Liu, Y., Zheng, Y., An, B., & Yang, Z. (2025) · Greenhouse Gases Science and Technology · doi:10.1002/ghg.2333 · Cited by 6
Gong, A., Jia, A., Wu, S., Fan, B., & Wei, X. (2025) · IEEE Access · doi:10.1109/access.2025.3552414 · Cited by 5
OmniLearn: A Framework for Distributed Deep Learning Over Heterogeneous Clusters
Tyagi, S., & Sharma, P. (2025) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2025.3553066 · Cited by 6
Improved Few‐Shot Object Detection Method Based on Faster R‐CNN
Wei, Y., Long, S., & Wang, Y. (2025) · IET Image Processing · doi:10.1049/ipr2.70038 · Cited by 5
UD-TN: A comprehensive ultrasound dataset for benign and malignant thyroid nodule classification
Zhu, J., Fu, X., Liu, Z., Chang, L., Li, X., Gao, J., Yu, R., & Wei, X. (2025) · Intelligent Oncology · doi:10.1016/j.intonc.2025.03.007 · Cited by 6
DFU-E: A Dataflow Architecture for Edge DSP and AI Applications
Li, W., Fan, Z., Liu, T., Wang, Z., Wu, H., Wu, M., Zhang, K., Liu, Y., Sun, N., Ye, X., et al. (2025) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2025.3555329 · Cited by 5
Analysis of a Memcapacitor‐Based Online Learning Neural Network Accelerator Framework
Singh, A., Kim, D., & Lee, B. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202400795 · Cited by 5
Apple Watercore Grade Classification Method Based on ConvNeXt and Visible/Near-Infrared Spectroscopy
Zhao, C., Yin, Z., Tan, Y., Zhang, W., Guo, P., Ma, Y., Wu, H., Ding, H., & Lu, Q. (2025) · Agriculture · doi:10.3390/agriculture15070756 · Cited by 5
Cai, S., Zhang, Q., Wang, S., Hu, J., Zeng, L., & Li, K. (2025) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.70077 · Cited by 7
Analyzing the performance of biomedical time-series segmentation with electrophysiology data
Ředina, R., Hejč, J., Filipenská, M., & Stárek, Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-90533-y · Cited by 6
Cai, J., Liu, W., Liu, T., et al. (2025) · Animals · doi:10.3390/ani15071067 · Cited by 6
Rathod, V. M., Patil, A. M., Motekar, H. S., et al. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20819-w · Cited by 5
Utilizing a deep learning model based on BERT for identifying enhancers and their strength
Wang, T., & Gao, M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0320085 · Cited by 7
Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
Rubin, R., Jacob, C., Sundar, S., et al. (2025) · Advances in Civil Engineering · doi:10.1155/adce/7911336 · Cited by 5
Tian, S., Ma, A., Zheng, Z., Tan, X., & Zhong, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3561021 · Cited by 8
Han, S., Ren, D., Gao, F., Yang, J., & Ma, H. (2025) · Remote Sensing · doi:10.3390/rs17081470 · Cited by 5
Üveges, I., & Ring, O. (2025) · Information · doi:10.3390/info16040330 · Cited by 10
Dual-branch adjacent connection and channel mixing network for video crowd counting
Ling, M., Chen, J., Liu, Y., Fang, W., & Geng, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111709 · Cited by 7
Xia, M., Zhang, Y., Peng, H. J., et al. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.113001 · Cited by 5
Tosoratti, E., Potthoff, U., Bennewitz, C., & Bambach, M. (2025) · Progress in Additive Manufacturing · doi:10.1007/s40964-025-01060-1 · Cited by 6
Jia, A., Sun, J., Du, B., & Lin, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3564647 · Cited by 5
Peilian, S., Zhao, S., Guo, L., Wang, D., Zhang, S., Zhao, X., Fang, J., Wang, G., Lu, H., & Yu, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127687 · Cited by 5
Kunz, P. C., Spohrer, K., & Heinzl, A. (2025) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2025.101902 · Cited by 7
MirageNet: improving the network performance of image understanding with very low FLOPs
Fu, Y., Liu, P. S., Lu, H., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128018 · Cited by 5
Wang, Z., Liu, J., Chen, F., Wang, W. K., Xu, Y., Lu, F., Li, Y., & Gao, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107926 · Cited by 7
Wrapped phase denoising: a WISE-transformer and comprehensive comparisons
Zou, Y., Lv, S., Tan, C., et al. (2025) · Optics Express · doi:10.1364/oe.563309 · Cited by 5
Optimizing Oral Cancer Detection: A Hybrid Feature Fusion using Local Binary Pattern and CNN
Kumar, J., Pandey, V., & Tiwari, R. K. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.283 · Cited by 7
Determination of the quality classes of Elazig cherry marble with image processing
Yavuz, M., & Türkoğlu, İ. (2025) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2025.103455 · Cited by 5
Saranya, S., Christy, S., & Kumari, V. S. (2025) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs65191.2025.10985225 · Cited by 6
Multi-domain fusion network: A novel approach to OCTA image segmentation in diabetic retinopathy
Jia, G., Ma, F., Li, S., Zhang, Z., Liu, H., Guo, Y., & Meng, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107945 · Cited by 5
Khobragade, R. H., Bhoyar, D. B., Paithane, A. N., et al. (2025) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2025.101015 · Cited by 5
Broad-ESN Based on Radical Activation Function for Predicting Time Series With Multiple Variables
Gong, Y., Lun, S., & Li, M. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3563937 · Cited by 7
Liu, J., Ren, K., & Chen, Q. (2025) · International Journal of Remote Sensing · doi:10.1080/01431161.2025.2506155 · Cited by 5
From Physically Based to Generative Models: A Survey on Underwater Image Synthesis Techniques
Barbosa, L. A., & Apolinário, A. L. (2025) · Journal of Imaging · doi:10.3390/jimaging11050161 · Cited by 5
Recognition of Machine-Readable Zone in Identity Documents: A Review
Gayer, A. V., Chernyshova, Y. S., & Arlazarov, V. V. (2025) · IEEE Access · doi:10.1109/access.2025.3571547 · Cited by 7
Xu, B., Pan, Y., Peng, J., et al. (2025) · International Journal of Refractory Metals and Hard Materials · doi:10.1016/j.ijrmhm.2025.107243 · Cited by 5
Wang, J.-X., Xiao, Y., Feng, J., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110563 · Cited by 4
Veluchamy, S., Bhuvaneswari, R., Ashwini, K., AlShathri, S. I., & El‐Shafai, W. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2025.102058 · Cited by 7
Haider, I., Khan, M. A., Masood, S., Algamdi, S. A., Alasiry, A., Marzougui, M., & Nam, Y. (2025) · Environmental Earth Sciences · doi:10.1007/s12665-025-12317-x · Cited by 6
A Modified Hierarchical Vision Transformer Model for Poultry Disease Detection
Soli, M. A. T., Agyei, D., Bandawu, W. U., et al. (2025) · IET Image Processing · doi:10.1049/ipr2.70115 · Cited by 5
Optimizing Remote Sensing Image Retrieval Through a Hybrid Methodology
Alegavi, S., & Sedamkar, R. (2025) · Journal of Imaging · doi:10.3390/jimaging11060179 · Cited by 5
Exploring geo-transferability of deep neural network by developing comprehensive metrics
Yu, J., Tu, W., Chen, X., Li, M., Chen, D., Cao, R., & Li, Q. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2505551 · Cited by 6
Quantum dual-branch neural networks with transfer learning for early detection of skin cancer
Sun, Y. (2025) · American Journal of Translational Research · doi:10.62347/wohq8174 · Cited by 5
Wang, X., Zhong, D., Liu, C., et al. (2025) · Remote Sensing · doi:10.3390/rs17111912 · Cited by 5
Self-Supervised Learning of Event-Guided Video Frame Interpolation for Rolling Shutter Frames
Lu, Y., Liang, G., Shen, Y., & Wang, L. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3576305 · Cited by 11
Abidoye, I., Ikeji, F., Coupland, C. A., Calaminus, S. D. J., Sander, N., & de Sousa, E. M. V. (2025) · Journal of Imaging · doi:10.3390/jimaging11060183 · Cited by 8
COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
Zhang, A., Yang, Z., Wang, N., Qi, Y., Xin, J. X., Li, X., & Yin, P. (2025) · IEEE Access · doi:10.1109/access.2025.3576737 · Cited by 13
Person re-identification based on an improved DeepLabv3+ semantic segmentation network
Zhu, F., Li, D., Li, H., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111384 · Cited by 5
Li, X., Deng, H., & Tang, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108088 · Cited by 5
Sağıroğlu, Ş., Terzi, R., Çeltikçi, E., Börcek, A. Ö., Atay, Y., Arslan, B., Şahin, M. Ç., Nernekli, K., Demirezen, M. U., Özdemir, O. B., et al. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2920 · Cited by 9
Wang, J., Zhang, S., Lai, J., et al. (2025) · Fuel · doi:10.1016/j.fuel.2025.135936 · Cited by 5
An image and text-based fake news detection with transfer learning
Setiawan, E. I., Sutanto, P., Purwanto, C. N., Santoso, J., Ferdinandus, F., Pah, N. D., & Purnomo, M. H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324394 · Cited by 9
“ViT has gained recognition for its effectiveness in handling the ImageNet dataset, which contains millions of labeled images and thousands of object categories [24].”
Multimodal latent emotion recognition from micro-expression and physiological signal
Zhang, L., Qian, Y., Arandjelović, O., et al. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111963 · Cited by 5
Similar concept matters: Prototype analogy for few-shot classification
Ouyang, T., Ma, B., & Xu, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130648 · Cited by 5
Wu, W., Chen, C.-C., Lin, M.-D., Lin, S.-L., & Lai, G. (2025) · Measurement · doi:10.1016/j.measurement.2025.118181 · Cited by 7
Fu, G., Zhang, Z., Li, J., Zhang, E., He, Z., Sun, F., Zhu, Q., Niu, F., Chen, H., & Shen, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128680 · Cited by 5
Characterizing DNA Origami Nanostructures in TEM Images Using Convolutional Neural Networks
Wei, X., Mo, Q., Chen, C., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00330 · Cited by 5
Anomaly recognition of magnetic flux leakage pipeline based on YOLO-GLW model
Wu, H., Yang, L., Geng, H., Shao, W., & Wu, X. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2522330 · Cited by 5
“In 2012, AlexNet [13], a convolutional neural network model with eight layers, tri-umphed in the ImageNet image classification contest, signifying the emergence of deep learning in computer vision.”
ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training
Wang, R., Yao, Q., Jiang, Z., Lai, H., He, Z., Tao, X., & Zhou, S. K. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103690 · Cited by 18
Esmeray, H., Doğan, Z., & İşeri, İ. (2025) · Evolving Systems · doi:10.1007/s12530-025-09710-z · Cited by 6
“Fine-tuning, part of transfer learning, is adjusting the model's hyperpa-rameters so that this pre-trained model better fits the new data set (Krizhevsky et al. 2017; Simonyan and Zisserman 1409).”
Bianco, R., Coluccia, S., Marinoni, M., et al. (2025) · Nutrients · doi:10.3390/nu17132196 · Cited by 5
“When applied to food images [12,15–17], DL outperforms traditional algorithms in extracting features from both generic [18] and food-specific images [12], eventually integrating vision– language models into this process [19].”
High-Order Temporal Context-Aware Aerial Tracking with Heterogeneous Visual Experts
Zhou, S., Fan, X., Wang, Z., Wang, W., & Zhang, Y. (2025) · Remote Sensing · doi:10.3390/rs17132237 · Cited by 7
Yang, C., Wei, C., Zhao, Y., Wang, L., Xu, P., Qi, K., Shao, Y., & Wu, H. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2514822 · Cited by 8
“Encouragingly, recent advancements in deep learning (DL) theory have pro-pelled classical models built upon CNN, such as AlexNet (Krizhevsky, Sutskever, and Hinton 2012), VGGNet (Zeiler and Fergus 2014), and ResNet (Wu et al. 2016), to the forefront of DL-based techniques.”
Dual decoding generative adversarial networks for infrared image enhancement
Yu, Y., Jiang, L., Hu, Q., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-06538-0 · Cited by 5
Keypoint-based modeling reveals fine-grained body pose tuning in superior temporal sulcus neurons
Raman, R., Bognár, A., Nejad, G. G., Mukovskiy, A., Martini, L. M., Giese, M. A., & Vogels, R. (2025) · Nature Communications · doi:10.1038/s41467-025-60945-5 · Cited by 6
SFP-Net: Scatter-feature-perception network for underwater image enhancement
Wang, Z., Guo, J., Zhang, J., Zhang, G., Yu, T., Zhao, S., & Zhu, D. (2025) · Displays · doi:10.1016/j.displa.2025.103132 · Cited by 5
SNR: One single network for image steganography with robust post-save recovery
Yang, C., Wang, S., Huang, Y., & Guo, M. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130929 · Cited by 8
Ouadou, A., Huangal, D., Alshehri, M., Scott, G. J., & Hurt, J. A. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3584877 · Cited by 7
Optical image processing and applications empowered by vision-language models
Xiao, J., Sun, Z., An, H., Zhao, H., Qiu, M., & Li, X. (2025) · iOptics · doi:10.1016/j.iopt.2025.100003 · Cited by 8
Olagunju, O., Stump, M., & Li, Y. (2025) · Agricultural Products Processing and Storage · doi:10.1007/s44462-025-00013-9 · Cited by 5
Hybrid transformer-CNN architecture for enhanced underwater image semantic segmentation
Zhang, J., Sun, Y., Wang, H., & Zhang, X. (2025) · The Visual Computer · doi:10.1007/s00371-025-04097-z · Cited by 6
Jia, J., Huang, J., Cui, Y., Zhang, D., Li, H., Wang, S., & Hang, W. (2025) · Digital Health · doi:10.1177/20552076251359498 · Cited by 7
Deep Learning Applications in the Analysis of Wear Mechanisms in Metallic Materials: A Review
Wang, X., Xiao, B., Zhang, B., Sun, R., Li, C., & Liaw, P. K. (2025) · ACS Materials Letters · doi:10.1021/acsmaterialslett.5c00688 · Cited by 7
Zhang, S., Ma, S., Luo, X., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111716 · Cited by 5
Lu, Y. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.06.053 · Cited by 5
RetractedLRP-QViT: Mixed-Precision Vision Transformer Quantization Using Layer Importance Score
Ranjan, N., & Savakis, A. E. (2025) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp65409.2025.11075195 · Cited by 11
“We evaluate LRP-QViT on ImageNet1K [35] using ViT [15], DeiT [16], and Swin [17].”
Application of Image Computing in Non-Destructive Detection of Chinese Cuisine
Huang, X., Li, Z., Li, Z., et al. (2025) · Foods · doi:10.3390/foods14142488 · Cited by 5
“In 2012, Krizhevsky et al. [55] introduced AlexNet, a groundbreaking CNN model that leveraged GPUs to significantly accelerate training processes.”
Liu, X., Kong, X., Xuan, W., Li, J., Nyakundi, A., Zhang, Y., Zheng, L., & Zhou, F. (2025) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2025.106620 · Cited by 7
Marques, C. S., Malafaia, E., Pereira, S., dos Santos, V. F., & Dufourq, E. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103329 · Cited by 5
Yun, H., Du, Q., Han, Z., Li, M., Yang, L., Liu, X., Wang, C., & Ma, W. (2025) · Sensors · doi:10.3390/s25154652 · Cited by 6
“CNNs [39] and Vision Transformers (ViTs) [40,41] are two commonly used backbone models for visual feature representation.”
Xu, Z., Xu, Y., Wang, M., Wei, L., Chen, J., & Wang, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114129 · Cited by 7
Vessel detection for maritime traffic management using U-Net with backbone networks
Kim, H.-C., Lee, H.-T., & Cho, I.-S. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121943 · Cited by 5
Li, H., Sahrani, S., Sarker, M. R., & Xiao, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3594091 · Cited by 6
Fatigue Life Prediction of CFRP-FBG Sensor-Reinforced RC Beams Enabled by LSTM-Based Deep Learning
Jia, M., Zhou, C., Pei, X., Xu, Z., Xu, W. B., & Wan, Z. (2025) · Polymers · doi:10.3390/polym17152112 · Cited by 8
“To alleviate this issue, Hinton et al. proposed the Dropout technique, a regularization method that randomly deactivates a fraction of neurons during training to reduce co-adaptation among neurons and improve the model’s generalization capability [28].”
Liu, R., Xiao, F., Zhang, J., et al. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112200 · Cited by 5
AI-driven plant disease detection with tailored convolutional neural network
Hassan, S. M., Nath, K. C., Jasiński, M., & Maji, A. K. (2025) · Network Computation in Neural Systems · doi:10.1080/0954898x.2025.2537680 · Cited by 5
Deng, M., Tan, X.-Y., Chen, K.-Q., Liu, B.-J., Zhao, Z.-Y., Tu, Y., Wu, S., Hu, X., & Zeng, Z. (2025) · International Journal of Geographical Information Science · doi:10.1080/13658816.2025.2541193 · Cited by 7
“…techniques are suitable for modeling the spatiotemporal characteristics within geographical data, such as CNNs for learning spatial dependencies (Krizhevsky et al. 2012) and recurrent neural networks (RNNs) for learning temporal dependencies (Williams and Zipser 1989; Sutskever et al. 2014).”
Wu, Q., Liu, W., Li, X., Su, Z., & Lei, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111705 · Cited by 11
Zhou, W., Shi, Z., Xie, B., Li, F., Yin, J., Zhang, Y., Hu, L., Li, L., Yan, Y., Wei, X., et al. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1622426 · Cited by 6
Emery, J. F., Le, M., Levy, J., et al. (2025) · Journal of the American Society of Cytopathology · doi:10.1016/j.jasc.2025.07.004 · Cited by 5
Multi-task cyclical consistency learning based medical image segmentation
Han, L., Zhang, J., Hu, Y., Liu, X., Yue, G., Wei, M., & Wu, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111863 · Cited by 5
Sperti, M., Cardaci, C., Bruno, F., Shah, S. T. H., Panagiotopoulos, K., Kassem, K., Nisco, G. D., Morbiducci, U., Piccolo, R., Burzotta, F., et al. (2025) · Reviews in Cardiovascular Medicine · doi:10.31083/rcm39210 · Cited by 7
“Popular networks employed in these techniques are AlexNet [94,95], Visual Geometry Group (VGG) models [95,96], and GoogleNet [97].”
Wu, Y.-M., Xie, Y., Xie, Y., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103496 · Cited by 5
Kasu, V. R., Malamuthu, B. K., Kumar, B. S., Pandi, V. S., Sivajothi, E., & Deepika, D. (2025) · Global Conference in Emerging Technology (GINOTECH) · doi:10.1109/ginotech63460.2025.11077035 · Cited by 5
Qiu, S., Yu, X., & Wu, Y. (2025) · Journal of Dentistry · doi:10.1016/j.jdent.2025.106027 · Cited by 9
Ensemble Intrusion Detection Based on Heterogeneous Data Augmentation and Knowledge Distillation
Wang, L.-H., Zhou, X., Ding, W.-P., et al. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3593924 · Cited by 3
Multi-task driver gaze estimation in real world driving scenes
Wu, X., Li, L., Zhou, G., Wu, Q., Zuo, X., Zhu, H., & He, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111892 · Cited by 6
MRR‐Assisted MZI Crossbar Array for Energy‐Efficient Optical Parallel Computing
Jiang, S., Liu, X., Wu, B., Sun, S., Zhou, H., Dong, J., & Zhang, X. (2025) · Laser & Photonics Review · doi:10.1002/lpor.202501035 · 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
