{"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/deep-convolutional-neural-networks-as-generic","title":"Deep Convolutional Neural Networks as Generic Feature Extractors","arxiv_id":"1710.02286","date":"2017-10-06","proceeding":null,"authors":["Lars Hertel","Erhardt Barth","Thomas Käster","Thomas Martinetz"],"abstract":"Recognizing objects in natural images is an intricate problem involving\nmultiple conflicting objectives. Deep convolutional neural networks, trained on\nlarge datasets, achieve convincing results and are currently the\nstate-of-the-art approach for this task. However, the long time needed to train\nsuch deep networks is a major drawback. We tackled this problem by reusing a\npreviously trained network. For this purpose, we first trained a deep\nconvolutional network on the ILSVRC2012 dataset. We then maintained the learned\nconvolution kernels and only retrained the classification part on different\ndatasets. Using this approach, we achieved an accuracy of 67.68 % on CIFAR-100,\ncompared to the previous state-of-the-art result of 65.43 %. Furthermore, our\nfindings indicate that convolutional networks are able to learn generic feature\nextractors that can be used for different tasks.","url_abs":"http://arxiv.org/abs/1710.02286v1","url_pdf":"http://arxiv.org/pdf/1710.02286v1.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":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"DCNN+GFE","rank_in_archive_order":210,"of":265,"metrics":{"Percentage correct":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"DCNN+GFE","rank_in_archive_order":183,"of":211,"metrics":{"Percentage correct":"67.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"DCNN+GFE","rank_in_archive_order":36,"of":81,"metrics":{"Percentage error":"0.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}