Open access
Aug 2026
Parameter-efficient cross-modal prompt tuning for few-shot ancient mural classification
PE-CPT adapts a pre-trained vision-language model by learning a small set of prompt vectors without updating its original parameters, and incorporates LoRA, a parameter-efficient adaptation method applied to attention and feed-forward layers to improve adaptation.
Donglai Fu, Chenlong Wang, Zixuan Li et al.
· npj Heritage Science · 0 citations