Prompt Learning via Meta-Regularization

arXiv:2404.00851v1 Announce Type: new
Abstract: Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks. However, most existing prompt learning methods suffer from task overfitting since the general knowledge of the pre-trained vision language models is forgotten while the prompts are finetuned on a small data set from a specific target task. To …

arxiv cs.cv meta prompt prompt learning regularization type via