{"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/cross-domain-ensemble-distillation-for-domain-2","title":"Cross-Domain Ensemble Distillation for Domain Generalization","arxiv_id":"2211.14058","date":"2022-11-25","proceeding":"European Conference on Computer Vision (ECCV) 2022 10","authors":["kyungmoon lee","Sungyeon Kim","Suha Kwak"],"abstract":"Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant features while encouraging the model to converge to flat minima, which recently turned out to be a sufficient condition for domain generalization. To this end, our method generates an ensemble of the output logits from training data with the same label but from different domains and then penalizes each output for the mismatch with the ensemble. Also, we present a de-stylization technique that standardizes features to encourage the model to produce style-consistent predictions even in an arbitrary target domain. Our method greatly improves generalization capability in public benchmarks for cross-domain image classification, cross-dataset person re-ID, and cross-dataset semantic segmentation. Moreover, we show that models learned by our method are robust against adversarial attacks and image corruptions.","url_abs":"https://arxiv.org/abs/2211.14058v1","url_pdf":"https://arxiv.org/pdf/2211.14058v1.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":"cross-domain-ensemble-distillation-for-domain-2","repo_url":"https://github.com/leekyungmoon/XDED","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-to-sketch-recognition","task_name":"Image to sketch recognition"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"single-source-domain-generalization","task_name":"Single-Source Domain Generalization"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"XDED (ResNet-18)","rank_in_archive_order":38,"of":45,"metrics":{"Average Accuracy":"67.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"XDED (ResNet-18)","rank_in_archive_order":48,"of":133,"metrics":{"Average Accuracy":"86.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-sketch-recognition-on-pacs","task":"Image to sketch recognition","dataset":"PACS","model":"XDED (ResNet18)","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"51.5"},"uses_additional_data":false},{"leaderboard":"/sota/single-source-domain-generalization-on-pacs","task":"Single-Source Domain Generalization","dataset":"PACS","model":"XDED (ResNet18)","rank_in_archive_order":6,"of":10,"metrics":{"Accuracy":"66.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.14058","atlas_url":"https://app.syntology.ai/?focus=2211.14058","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}