{"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/label-embedding-network-learning-label","title":"Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks","arxiv_id":"1710.10393","date":"2017-10-28","proceeding":"ICLR 2018 1","authors":["Xu Sun","Bingzhen Wei","Xuancheng Ren","Shuming Ma"],"abstract":"We propose a method, called Label Embedding Network, which can learn label\nrepresentation (label embedding) during the training process of deep networks.\nWith the proposed method, the label embedding is adaptively and automatically\nlearned through back propagation. The original one-hot represented loss\nfunction is converted into a new loss function with soft distributions, such\nthat the originally unrelated labels have continuous interactions with each\nother during the training process. As a result, the trained model can achieve\nsubstantially higher accuracy and with faster convergence speed. Experimental\nresults based on competitive tasks demonstrate the effectiveness of the\nproposed method, and the learned label embedding is reasonable and\ninterpretable. The proposed method achieves comparable or even better results\nthan the state-of-the-art systems. The source code is available at\n\\url{https://github.com/lancopku/LabelEmb}.","url_abs":"http://arxiv.org/abs/1710.10393v1","url_pdf":"http://arxiv.org/pdf/1710.10393v1.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":"label-embedding-network-learning-label","repo_url":"https://github.com/lancopku/LabelEmb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.10393","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}