{"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/embracenet-a-robust-deep-learning","title":"EmbraceNet: A robust deep learning architecture for multimodal classification","arxiv_id":"1904.09078","date":"2019-04-19","proceeding":null,"authors":["Jun-Ho Choi","Jong-Seok Lee"],"abstract":"Classification using multimodal data arises in many machine learning\napplications. It is crucial not only to model cross-modal relationship\neffectively but also to ensure robustness against loss of part of data or\nmodalities. In this paper, we propose a novel deep learning-based multimodal\nfusion architecture for classification tasks, which guarantees compatibility\nwith any kind of learning models, deals with cross-modal information carefully,\nand prevents performance degradation due to partial absence of data. We employ\ntwo datasets for multimodal classification tasks, build models based on our\narchitecture and other state-of-the-art models, and analyze their performance\non various situations. The results show that our architecture outperforms the\nother multimodal fusion architectures when some parts of data are not\navailable.","url_abs":"http://arxiv.org/abs/1904.09078v1","url_pdf":"http://arxiv.org/pdf/1904.09078v1.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":"embracenet-a-robust-deep-learning","repo_url":"https://github.com/gcunhase/embracebert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"embracenet-a-robust-deep-learning","repo_url":"https://github.com/idearibosome/embracenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"embracenet","method_name":"EmbraceNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"embracenet","name":"EmbraceNet","full_name":"EmbraceNet: A robust deep learning architecture for multimodal classification"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.09078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}