Papers › ImageNet Classification with Deep Convolutional Neural Networks

ImageNet Classification with Deep Convolutional Neural Networks

1 Dec 2012NeurIPS 2012 12archive 2025-07-28

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7\% and 18.9\% which is considerably better than the previous state-of-the-art results. The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and two globally connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets. To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective.

PaperPDFCode

Code

23 repositories listed; official and paper-mentioned ones first.

PaddlePaddle/PaddleClas paddleApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 report
pwc-1/Paper-9 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationGraph ClassificationImage ClassificationObject Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification BP-fMRI-97 CNN Accuracy 54.6% #5 of 7 Archive leaderboard report
Graph Classification BP-fMRI-97 CNN F1 52.8% #5 of 7 Archive leaderboard report
Graph Classification HIV-DTI-77 CNN Accuracy 54.3% #5 of 6 Archive leaderboard report
Graph Classification HIV-DTI-77 CNN F1 55.7% #5 of 6 Archive leaderboard report
Graph Classification HIV-fMRI-77 CNN Accuracy 59.3% #4 of 7 Archive leaderboard report
Graph Classification HIV-fMRI-77 CNN F1 66.3% #4 of 7 Archive leaderboard report
Image Classification CIFAR-10 DCNN Percentage correct 89 #211 of 265 Archive leaderboard report
Image Classification ImageNet ReaL AlexNet Accuracy 62.88% #53 of 57 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home AlexNet [cite:NIPS12CNN] Accuracy 54.9 #18 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Grouped Convolution, Large Kernel Size, Local Response Normalization

ConvolutionDense ConnectionsGrouped ConvolutionLAMBLarge Kernel SizeLocal Response NormalizationMax PoolingRandom Horizontal FlipRandom Resized CropReLUSGD with MomentumSoftmaxStep DecayWeight Decay

1 archive method tag without a method page not shown.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections