论文标题
神经及时搜索
Neural Prompt Search
论文作者
论文摘要
在过去的几年中，视觉模型的规模呈指数增长，尤其是在视觉变压器出现之后。这激发了参数有效调整方法的开发，例如学习适配器层或视觉及时令牌，这允许训练一小部分模型参数，而从预训练中获得的绝大多数则可以冷冻。但是，设计适当的调整方法并非平凡：可能需要尝试冗长的设计选择列表，更不用说每个下游数据集通常都需要自定义设计。在本文中，我们将现有的参数效率调整方法视为“提示模块”，并提出了神经及时搜索（Noah），这是一种新颖的方法，可以通过神经体系结构搜索算法，专门针对每个下游数据集来学习大型视觉模型的最佳及时模型设计。通过对20多个视觉数据集进行大量实验，我们证明了Noah（i）优于单个提示模块，（ii）具有良好的少数学习能力，并且（iii）可以域名。代码和型号可在https://github.com/davidzhangyuanhan/noah上找到。
The size of vision models has grown exponentially over the last few years, especially after the emergence of Vision Transformer. This has motivated the development of parameter-efficient tuning methods, such as learning adapter layers or visual prompt tokens, which allow a tiny portion of model parameters to be trained whereas the vast majority obtained from pre-training are frozen. However, designing a proper tuning method is non-trivial: one might need to try out a lengthy list of design choices, not to mention that each downstream dataset often requires custom designs. In this paper, we view the existing parameter-efficient tuning methods as "prompt modules" and propose Neural prOmpt seArcH (NOAH), a novel approach that learns, for large vision models, the optimal design of prompt modules through a neural architecture search algorithm, specifically for each downstream dataset. By conducting extensive experiments on over 20 vision datasets, we demonstrate that NOAH (i) is superior to individual prompt modules, (ii) has a good few-shot learning ability, and (iii) is domain-generalizable. The code and models are available at https://github.com/Davidzhangyuanhan/NOAH.
