Proceedings

Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models

Rui Zhu, Song-Lin Lv, Zi-Kang Wang, Lan-Zhe Guo

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 5448-5456.

https://doi.org/10.24963/ijcai.2026/607

Keywords

  • Machine Learning: Semi-supervised learning
  • Machine Learning: Multi-modal learning

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.

Rui Zhu, Song-Lin Lv, Zi-Kang Wang, and Lan-Zhe Guo. 2026. Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 5448–5456. https://doi.org/10.24963/ijcai.2026/607
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards