{"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-co-training-for-semi-supervised-image","title":"Deep Co-Training for Semi-Supervised Image Recognition","arxiv_id":"1803.05984","date":"2018-03-15","proceeding":"ECCV 2018 9","authors":["Siyuan Qiao","Wei Shen","Zhishuai Zhang","Bo wang","Alan Yuille"],"abstract":"In this paper, we study the problem of semi-supervised image recognition,\nwhich is to learn classifiers using both labeled and unlabeled images. We\npresent Deep Co-Training, a deep learning based method inspired by the\nCo-Training framework. The original Co-Training learns two classifiers on two\nviews which are data from different sources that describe the same instances.\nTo extend this concept to deep learning, Deep Co-Training trains multiple deep\nneural networks to be the different views and exploits adversarial examples to\nencourage view difference, in order to prevent the networks from collapsing\ninto each other. As a result, the co-trained networks provide different and\ncomplementary information about the data, which is necessary for the\nCo-Training framework to achieve good results. We test our method on SVHN,\nCIFAR-10/100 and ImageNet datasets, and our method outperforms the previous\nstate-of-the-art methods by a large margin.","url_abs":"http://arxiv.org/abs/1803.05984v1","url_pdf":"http://arxiv.org/pdf/1803.05984v1.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":"deep-co-training-for-semi-supervised-image","repo_url":"https://github.com/AlanChou/Deep-Co-Training-for-Semi-Supervised-Image-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.05984","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}