Bi-CoG improves semi-supervised fine-tuning of vision-language models by assigning higher-quality pseudo-labels through simultaneous inter-model and intra-model consistency checks combined with dynamic error-aware selection.
InInterna- tional Conference on Learning Representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models
Bi-CoG improves semi-supervised fine-tuning of vision-language models by assigning higher-quality pseudo-labels through simultaneous inter-model and intra-model consistency checks combined with dynamic error-aware selection.