Adapting Multimodal Foundation Models for Few-Shot Learning: A Comprehensive Study on Contrastive Captioners

N. K. B. M. P. K. B. Narasinghe, Uthayasanker Thayasivam

Large-scale multimodal foundation models, particularly Contrastive Captioners (CoCa), have achieved state-of-the-art results by unifying contrastive alignment with generative capti…