{"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/choicenet-robust-learning-by-revealing-output","title":"Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks","arxiv_id":"1805.06431","date":"2018-05-16","proceeding":"CVPR 2020 6","authors":["Sungjoon Choi","Sanghoon Hong","Kyungjae Lee","Sungbin Lim"],"abstract":"In this paper, we focus on weakly supervised learning with noisy training data for both classification and regression problems.We assume that the training outputs are collected from a mixture of a target and correlated noise distributions.Our proposed method simultaneously estimates the target distribution and the quality of each data which is defined as the correlation between the target and data generating distributions.The cornerstone of the proposed method is a Cholesky Block that enables modeling dependencies among mixture distributions in a differentiable manner where we maintain the distribution over the network weights.We first provide illustrative examples in both regression and classification tasks to show the effectiveness of the proposed method.Then, the proposed method is extensively evaluated in a number of experiments where we show that it constantly shows comparable or superior performances compared to existing baseline methods in the handling of noisy data.","url_abs":"https://arxiv.org/abs/1805.06431v4","url_pdf":"https://arxiv.org/pdf/1805.06431v4.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":"choicenet-robust-learning-by-revealing-output","repo_url":"https://github.com/sjchoi86/choicenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.06431","atlas_url":"https://app.syntology.ai/?focus=1805.06431","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}