AAPL: Adding Attributes to Prompt Learning for Vision-Language Models

arXiv:2404.16804v1 Announce Type: cross
Abstract: Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where context within a prompt is replaced with learnable vectors, leading to significant improvements over manually crafted prompts. However, the performance improvement for unseen classes is still marginal, and to tackle this problem, data augmentation has been frequently used in traditional zero-shot learning …

abstract advances arxiv building context cs.ai cs.cv cs.lg improvements language language models performance prompt prompt learning studies tasks type vectors vision vision-language vision-language models zero-shot