{"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/meta-convolutional-neural-networks-for-single","title":"Meta Convolutional Neural Networks for Single Domain Generalization","arxiv_id":null,"date":"2022-01-01","proceeding":"CVPR 2022 1","authors":["Chaoqun Wan","Xu Shen","Yonggang Zhang","Zhiheng Yin","Xinmei Tian","Feng Gao","Jianqiang Huang","Xian-Sheng Hua"],"abstract":"    In single domain generalization, models trained with data from only one domain are required to perform well on many unseen domains. In this paper, we propose a new model, termed meta convolutional neural network, to solve the single domain generalization problem in image recognition. The key idea is to decompose the convolutional features of images into meta features. Acting as \"visual words\", meta features are defined as universal and basic visual elements for image representations (like words for documents in language). Taking meta features as reference, we propose compositional operations to eliminate irrelevant features of local convolutional features by an addressing process and then to reformulate the convolutional feature maps as a composition of related meta features. In this way, images are universally coded without biased information from the unseen domain, which can be processed by following modules trained in the source domain. The compositional operations adopt a regression analysis technique to learn the meta features in an online batch learning manner. Extensive experiments on multiple benchmark datasets verify the superiority of the proposed model in improving single domain generalization ability.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2022/html/Wan_Meta_Convolutional_Neural_Networks_for_Single_Domain_Generalization_CVPR_2022_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2022/papers/Wan_Meta_Convolutional_Neural_Networks_for_Single_Domain_Generalization_CVPR_2022_paper.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"},{"task_slug":"photo-to-rest-generalization","task_name":"Photo to Rest Generalization"},{"task_slug":"single-source-domain-generalization","task_name":"Single-Source Domain Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/photo-to-rest-generalization-on-pacs","task":"Photo to Rest Generalization","dataset":"PACS","model":"MetaCNN (AlexNet)","rank_in_archive_order":6,"of":8,"metrics":{"Accuracy":"57.17"},"uses_additional_data":false},{"leaderboard":"/sota/single-source-domain-generalization-on-digits","task":"Single-Source Domain Generalization","dataset":"Digits-five","model":"MetaCNN (LeNet)","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"78.76"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}