{"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/domain-generalization-with-domain-specific","title":"Domain Generalization with Domain-Specific Aggregation Modules","arxiv_id":"1809.10966","date":"2018-09-28","proceeding":null,"authors":["Antonio D'Innocente","Barbara Caputo"],"abstract":"Visual recognition systems are meant to work in the real world. For this to\nhappen, they must work robustly in any visual domain, and not only on the data\nused during training. Within this context, a very realistic scenario deals with\ndomain generalization, i.e. the ability to build visual recognition algorithms\nable to work robustly in several visual domains, without having access to any\ninformation about target data statistic. This paper contributes to this\nresearch thread, proposing a deep architecture that maintains separated the\ninformation about the available source domains data while at the same time\nleveraging over generic perceptual information. We achieve this by introducing\ndomain-specific aggregation modules that through an aggregation layer strategy\nare able to merge generic and specific information in an effective manner.\nExperiments on two different benchmark databases show the power of our\napproach, reaching the new state of the art in domain generalization.","url_abs":"http://arxiv.org/abs/1809.10966v1","url_pdf":"http://arxiv.org/pdf/1809.10966v1.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":[],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"D-SAM-Λ  (Resnet-18)","rank_in_archive_order":91,"of":133,"metrics":{"Average Accuracy":"80.72"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"D-SAM (Alexnet)","rank_in_archive_order":118,"of":133,"metrics":{"Average Accuracy":"71.20"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.10966","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}