{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/imagenet-classification-with-deep","title":"ImageNet Classification with Deep Convolutional Neural Networks","arxiv_id":null,"date":"2012-12-01","proceeding":"NeurIPS 2012 12","authors":["Alex Krizhevsky","Ilya Sutskever","Geoffrey E. Hinton"],"abstract":"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.","url_abs":"http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks","url_pdf":"http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://worksheets.codalab.org/worksheets/0xfafccca55b584e6eb1cf71979ad8e778","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/2023-MindSpore-1/ms-code-123","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/2023-MindSpore-1/ms-code-86","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/2023-MindSpore-4/Code8/tree/main/Alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/2024-MindSpore-1/Code5/tree/main/Alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/EverLookNeverSee/diag2model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/Mayurji/Image-Classification-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/MindCode-4/code-10/tree/main/Alexnet-ABeffect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/Alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/Shorouq-Aliyan/classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/code-implementation1/Code2/tree/main/Alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/computerhistory/AlexNet-Source-Code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/dansuh17/alexnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/demul/AlexNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/gchaperon/alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/kingcong/alexnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/Alexnet/src","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/mindspore-courses/heads-on-mindspore/blob/main/1-best-practice/models/alexnet.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/6/Alexnet-ABeffect/test50_feature","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://github.com/pytorch/vision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"imagenet-classification-with-deep","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":null,"method_name":"(USA Guide)"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"lamb","method_name":"LAMB"},{"method_slug":"large-kernel-size","method_name":"Large Kernel Size"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"grouped-convolution","name":"Grouped Convolution","full_name":"Grouped Convolution"},{"slug":"large-kernel-size","name":"Large Kernel Size","full_name":"Large convolutional kernels"},{"slug":"local-response-normalization","name":"Local Response Normalization","full_name":"Local Response Normalization"}],"results":[{"leaderboard":"/sota/graph-classification-on-bp-fmri-97","task":"Graph Classification","dataset":"BP-fMRI-97","model":"CNN","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"54.6%","F1":"52.8%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-hiv-dti-77","task":"Graph Classification","dataset":"HIV-DTI-77","model":"CNN","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"54.3%","F1":"55.7%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-hiv-fmri-77","task":"Graph Classification","dataset":"HIV-fMRI-77","model":"CNN","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"59.3%","F1":"66.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"DCNN","rank_in_archive_order":211,"of":265,"metrics":{"Percentage correct":"89"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"AlexNet","rank_in_archive_order":53,"of":57,"metrics":{"Accuracy":"62.88%"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-office-home","task":"Unsupervised Domain Adaptation","dataset":"Office-Home","model":"AlexNet [cite:NIPS12CNN]","rank_in_archive_order":18,"of":20,"metrics":{"Accuracy":"54.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}