{"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/toward-robustness-against-label-noise-in","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","arxiv_id":"1706.00038","date":"2017-05-31","proceeding":"NeurIPS 2017 12","authors":["Arash Vahdat"],"abstract":"Collecting large training datasets, annotated with high-quality labels, is\ncostly and time-consuming. This paper proposes a novel framework for training\ndeep convolutional neural networks from noisy labeled datasets that can be\nobtained cheaply. The problem is formulated using an undirected graphical model\nthat represents the relationship between noisy and clean labels, trained in a\nsemi-supervised setting. In our formulation, the inference over latent clean\nlabels is tractable and is regularized during training using auxiliary sources\nof information. The proposed model is applied to the image labeling problem and\nis shown to be effective in labeling unseen images as well as reducing label\nnoise in training on CIFAR-10 and MS COCO datasets.","url_abs":"http://arxiv.org/abs/1706.00038v2","url_pdf":"http://arxiv.org/pdf/1706.00038v2.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":"toward-robustness-against-label-noise-in","repo_url":"https://github.com/Gabriel-Macias/robust_frcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00038","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}