{"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/transfer-learning-of-artist-group-factors-to","title":"Transfer Learning of Artist Group Factors to Musical Genre Classification","arxiv_id":"1805.02043","date":"2018-05-05","proceeding":null,"authors":["Jaehun Kim","Minz Won","Xavier Serra","Cynthia C. S. Liem"],"abstract":"The automated recognition of music genres from audio information is a\nchallenging problem, as genre labels are subjective and noisy. Artist labels\nare less subjective and less noisy, while certain artists may relate more\nstrongly to certain genres. At the same time, at prediction time, it is not\nguaranteed that artist labels are available for a given audio segment.\nTherefore, in this work, we propose to apply the transfer learning framework,\nlearning artist-related information which will be used at inference time for\ngenre classification. We consider different types of artist-related\ninformation, expressed through artist group factors, which will allow for more\nefficient learning and stronger robustness to potential label noise.\nFurthermore, we investigate how to achieve the highest validation accuracy on\nthe given FMA dataset, by experimenting with various kinds of transfer methods,\nincluding single-task transfer, multi-task transfer and finally multi-task\nlearning.","url_abs":"http://arxiv.org/abs/1805.02043v2","url_pdf":"http://arxiv.org/pdf/1805.02043v2.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":"transfer-learning-of-artist-group-factors-to","repo_url":"https://github.com/mmwebster/variable-transfer-genre","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"genre-classification","task_name":"Genre classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}