SelfPrompt combines cluster-based pseudo-labelling with confidence-aware learning to improve semi-supervised prompt tuning of CLIP-style vision-language models.
Both GRIP and CPL adopt an iterative process, where the model is used to continuously refine and select additional samples from the unlabelled set
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SelfPrompt: Confidence-Aware Semi-Supervised Tuning for Robust Vision-Language Model Adaptation
SelfPrompt combines cluster-based pseudo-labelling with confidence-aware learning to improve semi-supervised prompt tuning of CLIP-style vision-language models.