{"type":"ScholarlyArticle","title":"Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models","authors":[{"name":"Rui Zhu","slug":"rui-zhu","given":"Rui","family":"Zhu","affiliation":""},{"name":"Song-Lin Lv","slug":"song-lin-lv","given":"Song-Lin","family":"Lv","affiliation":""},{"name":"Zi-Kang Wang","slug":"zi-kang-wang","given":"Zi-Kang","family":"Wang","affiliation":""},{"name":"Lan-Zhe Guo","slug":"lan-zhe-guo","given":"Lan-Zhe","family":"Guo","affiliation":""}],"abstract":"Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining fine-tuning of pre-trained vision-language models (VLMs) with SSL, forming the emerging paradigm of semi-supervised fine-tuning. However, existing methods often suffer from model bias and hyperparameter sensitivity, due to reliance on prediction consistency or pre-defined confidence thresholds. To address these limitations, we propose a simple yet effective plug-and-play methodology named Bi-Consistency-Guided Self-Training (Bi-CoG), which assigns high-quality and low-bias pseudo-labels, by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy. Both theoretical analysis and extensive experiments over 14 datasets demonstrate the effectiveness of Bi-CoG, which consistently and significantly improves the performance of existing methods.","doi":"10.24963/ijcai.2026/607","url":"https://ijcai.org/proceedings/2026/607","pdf":"https://ijcai.org/proceedings/2026/0607.pdf","markdown":"https://ijcai.org/proceedings/2026/607.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/607","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":607,"pages":{"first":5448,"last":5456},"keywords":["Machine Learning: Semi-supervised learning","Machine Learning: Multi-modal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}