{"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/repetitive-reprediction-deep-decipher-for","title":"Repetitive Reprediction Deep Decipher for Semi-Supervised Learning","arxiv_id":"1908.04345","date":"2019-08-09","proceeding":null,"authors":["Guo-Hua Wang","Jianxin Wu"],"abstract":"Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parameters iteratively. However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels. In this paper, we propose a principled end-to-end framework named deep decipher (D2) for SSL. Within the D2 framework, we prove that pseudo-labels are related to network predictions by an exponential link function, which gives a theoretical support for using predictions as pseudo-labels. Furthermore, we demonstrate that updating pseudo-labels by network predictions will make them uncertain. To mitigate this problem, we propose a training strategy called repetitive reprediction (R2). Finally, the proposed R2-D2 method is tested on the large-scale ImageNet dataset and outperforms state-of-the-art methods by 5 percentage points.","url_abs":"https://arxiv.org/abs/1908.04345v2","url_pdf":"https://arxiv.org/pdf/1908.04345v2.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":"repetitive-reprediction-deep-decipher-for","repo_url":"https://github.com/DoctorKey/R2D2.pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"R2-D2 (Shake-Shake)","rank_in_archive_order":26,"of":49,"metrics":{"Percentage error":"5.72"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"R2-D2 (ResNet-18)","rank_in_archive_order":53,"of":75,"metrics":{"Top 5 Accuracy":"90.48%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"R2-D2 (CNN-13)","rank_in_archive_order":10,"of":17,"metrics":{"Accuracy":"96.36"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"R2-D2 (CNN-13)","rank_in_archive_order":26,"of":29,"metrics":{"Percentage error":"32.87"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.04345","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}