{"type":"ScholarlyArticle","title":"Open-World Semi-Supervised Learning with Class Semantic Correlations","authors":[{"name":"Yuxin Fan","slug":"yuxin-fan","given":"Yuxin","family":"Fan","affiliation":""},{"name":"Junbiao Cui","slug":"junbiao-cui","given":"Junbiao","family":"Cui","affiliation":""},{"name":"Jiye Liang","slug":"jiye-liang","given":"Jiye","family":"Liang","affiliation":""},{"name":"Jianqing Liang","slug":"jianqing-liang","given":"Jianqing","family":"Liang","affiliation":""}],"abstract":"Open-world semi-supervised learning (OWSSL) aims to recognize both known and unknown classes, but the labeled samples only cover the known classes. Existing OWSSL methods primarily represent classes as symbolic variables, which ignore the rich internal semantic information associated with the classes and thus hampers their ability to recognize unknown classes. Recent studies incorporate textual descriptions of classes to facilitate training, but these methods overlook the class semantic correlations, which constrains their effectiveness in recognizing unknown classes. To address these issues, we propose a novel OWSSL method. Our method fine-tunes only the image encoder during training while keeping the text encoder frozen, thereby preserving the rich semantic correlations learned during the pre-training phase. Furthermore, we employ a semantic margin to extract class semantic correlations from textual descriptions, which are then utilized in enhancing image representation discriminability. Experimental results across multiple datasets demonstrate that our method significantly outperforms representative OWSSL methods in the recognition of both known and unknown classes.","doi":"10.24963/ijcai.2025/567","url":"https://ijcai.org/proceedings/2025/567","pdf":"https://ijcai.org/proceedings/2025/0567.pdf","markdown":"https://ijcai.org/proceedings/2025/567.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/567","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":"Machine Learning","track":"Main Track","number":567,"pages":{"first":5092,"last":5100},"keywords":["Machine Learning: ML: Semi-supervised learning","Machine Learning: ML: Open-World/Open-Set/OOD Learning","Machine Learning: ML: Weakly supervised learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}