{"type":"ScholarlyArticle","title":"Indirect Alignment and Relationship Preservation for Domain Generalization","authors":[{"name":"Wei Wei","slug":"wei-wei","given":"Wei","family":"Wei","affiliation":""},{"name":"Zixiong Li","slug":"zixiong-li","given":"Zixiong","family":"Li","affiliation":""},{"name":"Jing Yan","slug":"jing-yan","given":"Jing","family":"Yan","affiliation":""},{"name":"Mingwen Shao","slug":"mingwen-shao","given":"Mingwen","family":"Shao","affiliation":""},{"name":"Lin Li","slug":"lin-li","given":"Lin","family":"Li","affiliation":""}],"abstract":"Domain generalization (DG) aims to train models on multiple source domains to generalize effectively to unseen target domains, addressing performance degradation caused by domain shifts. Many existing methods rely on direct feature alignment, which disrupts natural sequence relationships, causes misalignment and feature distortion, and leads to overfitting, especially with significant domain gaps. To tackle these issues, we propose a novel DG approach with two key modules: the Sample Difference Keeping (SDK) module, which preserves natural sequence relationships to enhance feature diversity and separability, and the Sample Consistency Alignment (SCA) module, which achieves indirect alignment by modeling inter-class and inter-domain relationship consistencies. This approach mitigates overfitting and misalignment, ensuring adaptability to significant domain gaps. Extensive experiments demonstrate that our framework consistently outperforms state-of-the-art methods.","doi":"10.24963/ijcai.2025/229","url":"https://ijcai.org/proceedings/2025/229","pdf":"https://ijcai.org/proceedings/2025/0229.pdf","markdown":"https://ijcai.org/proceedings/2025/229.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/229","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":229,"pages":{"first":2054,"last":2062},"keywords":["Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: CV: Machine learning for vision","Machine Learning: ML: Classification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}