{"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/rethinking-recurrent-neural-networks-and","title":"Rethinking Recurrent Neural Networks and Other Improvements for Image Classification","arxiv_id":"2007.15161","date":"2020-07-30","proceeding":null,"authors":["Nguyen Huu Phong","Bernardete Ribeiro"],"abstract":"Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D images, these networks are used merely to learn and generate data sequentially rather than for image recognition tasks. In this study, we propose integrating an RNN as an additional layer when designing image recognition models. We also develop end-to-end multimodel ensembles that produce expert predictions using several models. In addition, we extend the training strategy so that our model performs comparably to leading models and can even match the state-of-the-art models on several challenging datasets (e.g., SVHN (0.99), Cifar-100 (0.9027) and Cifar-10 (0.9852)). Moreover, our model sets a new record on the Surrey dataset (0.949). The source code of the methods provided in this article is available at https://github.com/leonlha/e2e-3m and http://nguyenhuuphong.me.","url_abs":"https://arxiv.org/abs/2007.15161v3","url_pdf":"https://arxiv.org/pdf/2007.15161v3.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":"rethinking-recurrent-neural-networks-and","repo_url":"https://github.com/leonlha/e2e-3m","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"E2E-3M","rank_in_archive_order":39,"of":265,"metrics":{"Percentage correct":"98.52"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"E2E-3M","rank_in_archive_order":24,"of":211,"metrics":{"Percentage correct":"90.27"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-fashion-mnist","task":"Image Classification","dataset":"Fashion-MNIST","model":"E2E-3M","rank_in_archive_order":3,"of":34,"metrics":{"Percentage error":"4.08"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"E2E-M3","rank_in_archive_order":1,"of":62,"metrics":{"Percentage error":"1.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-surrey-asl","task":"Image Classification","dataset":"Surrey ASL","model":"E2E-3M","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"94.90"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-icassava-19","task":"Image Classification","dataset":"iCassava'19","model":"E2E-3M","rank_in_archive_order":1,"of":1,"metrics":{"Top-1 Accuracy":"0.9368"},"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}