{"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/enaet-self-trained-ensemble-autoencoding","title":"EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations","arxiv_id":"1911.09265","date":"2019-11-21","proceeding":null,"authors":["Xiao Wang","Daisuke Kihara","Jiebo Luo","Guo-Jun Qi"],"abstract":"Deep neural networks have been successfully applied to many real-world applications. However, such successes rely heavily on large amounts of labeled data that is expensive to obtain. Recently, many methods for semi-supervised learning have been proposed and achieved excellent performance. In this study, we propose a new EnAET framework to further improve existing semi-supervised methods with self-supervised information. To our best knowledge, all current semi-supervised methods improve performance with prediction consistency and confidence ideas. We are the first to explore the role of {\\bf self-supervised} representations in {\\bf semi-supervised} learning under a rich family of transformations. Consequently, our framework can integrate the self-supervised information as a regularization term to further improve {\\it all} current semi-supervised methods. In the experiments, we use MixMatch, which is the current state-of-the-art method on semi-supervised learning, as a baseline to test the proposed EnAET framework. Across different datasets, we adopt the same hyper-parameters, which greatly improves the generalization ability of the EnAET framework. Experiment results on different datasets demonstrate that the proposed EnAET framework greatly improves the performance of current semi-supervised algorithms. Moreover, this framework can also improve {\\bf supervised learning} by a large margin, including the extremely challenging scenarios with only 10 images per class. The code and experiment records are available in \\url{https://github.com/maple-research-lab/EnAET}.","url_abs":"https://arxiv.org/abs/1911.09265v2","url_pdf":"https://arxiv.org/pdf/1911.09265v2.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":"enaet-self-trained-ensemble-autoencoding","repo_url":"https://github.com/maple-research-lab/EnAET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enaet-self-trained-ensemble-autoencoding","repo_url":"https://github.com/wang3702/EnAET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"EnAET","rank_in_archive_order":57,"of":265,"metrics":{"Percentage correct":"98.01"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"EnAET","rank_in_archive_order":91,"of":211,"metrics":{"Percentage correct":"83.13"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"EnAET","rank_in_archive_order":16,"of":117,"metrics":{"Percentage correct":"95.48"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"EnAET","rank_in_archive_order":32,"of":62,"metrics":{"Percentage error":"2.22"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"EnAET","rank_in_archive_order":14,"of":49,"metrics":{"Percentage error":"4.18"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-3","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 1000 Labels","model":"EnAET","rank_in_archive_order":1,"of":1,"metrics":{"Percentage correct":"41.27"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-4","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 5000Labels","model":"EnAET","rank_in_archive_order":2,"of":2,"metrics":{"Percentage correct":"68.17"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-stl","task":"Semi-Supervised Image Classification","dataset":"STL-10","model":"EnAET","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"95.48"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-stl-1","task":"Semi-Supervised Image Classification","dataset":"STL-10, 1000 Labels","model":"EnAET","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy":"91.96"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"EnAET","rank_in_archive_order":4,"of":17,"metrics":{"Accuracy":"97.58"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"EnAET","rank_in_archive_order":5,"of":15,"metrics":{"Accuracy":"96.79"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"EnAET (WRN-28-2-Large)","rank_in_archive_order":17,"of":29,"metrics":{"Percentage error":"22.92"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"EnAET (WRN-28-2)","rank_in_archive_order":23,"of":29,"metrics":{"Percentage error":"26.93±0.21"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-3","task":"Semi-Supervised Image Classification","dataset":"cifar10, 250 Labels","model":"EnAET","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"92.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.09265","atlas_url":"https://app.syntology.ai/?focus=1911.09265","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}