AINeutralarXiv – CS AI · 10h ago6/10
🧠
Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise
Researchers introduce VisPrompt, a framework that improves prompt learning for vision-language models by injecting visual semantic information to enhance robustness against label noise. The approach keeps pre-trained models frozen while adding minimal trainable parameters, demonstrating superior performance across seven benchmark datasets under both synthetic and real-world noisy conditions.