BriefGPT.xyz
Dec, 2023
LaViP: 语言驱动的视觉提示
LaViP:Language-Grounded Visual Prompts
HTML
PDF
Nilakshan Kunananthaseelan, Jing Zhang, Mehrtash Harandi
TL;DR
通过语言引导的视觉提示方法，我们使视觉语言模型的视觉编码器适应下游任务，从而提高适应性和泛化性能。
Abstract
We introduce a
language-grounded visual prompting
method to adapt the visual encoder of
vision-language models
for downstream tasks. By capitalizing on language integration, we devise a parameter-efficient strate
→