{"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/unsupervised-adversarial-domain-adaptation","title":"Unsupervised adversarial domain adaptation for acoustic scene classification","arxiv_id":"1808.05777","date":"2018-08-17","proceeding":null,"authors":["Shayan Gharib","Konstantinos Drossos","Emre Çakır","Dmitriy Serdyuk","Tuomas Virtanen"],"abstract":"A general problem in acoustic scene classification task is the mismatched\nconditions between training and testing data, which significantly reduces the\nperformance of the developed methods on classification accuracy. As a\ncountermeasure, we present the first method of unsupervised adversarial domain\nadaptation for acoustic scene classification. We employ a model pre-trained on\ndata from one set of conditions and by using data from other set of conditions,\nwe adapt the model in order that its output cannot be used for classifying the\nset of conditions that input data belong to. We use a freely available dataset\nfrom the DCASE 2018 challenge Task 1, subtask B, that contains data from\nmismatched recording devices. We consider the scenario where the annotations\nare available for the data recorded from one device, but not for the rest. Our\nresults show that with our model agnostic method we can achieve $\\sim 10\\%$\nincrease at the accuracy on an unseen and unlabeled dataset, while keeping\nalmost the same performance on the labeled dataset.","url_abs":"http://arxiv.org/abs/1808.05777v1","url_pdf":"http://arxiv.org/pdf/1808.05777v1.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":"unsupervised-adversarial-domain-adaptation","repo_url":"https://github.com/shayangharib/AUDASC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"acoustic-scene-classification","task_name":"Acoustic Scene Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"scene-classification","task_name":"Scene Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}