With the introduction of the transformer architecture in computer vision,
increasing model scale has been demonstrated as a clear path to achieving
performance and robustness gains. However, with model parameter counts reaching
the billions, classical finetuning approaches are becoming increasingly
limiting and even unfeasible when models become hosted as inference APIs, as in
NLP. To this end, visual prompt learning, whereby a model is adapted by
learning additional inputs, has emerged as a potential solution for adapting
frozen and cloud-hosted models: During inference, this neither requires access
to the internals of models' forward pass function, nor requires any
post-processing. In this work, we propose the Prompt Generation Network (PGN)
that generates high performing, input-dependent prompts by sampling from an
end-to-end learned library of tokens. We further introduce the "prompt
inversion" trick, with which PGNs can be efficiently trained in a latent space
but deployed as strictly input-only prompts for inference. We show the PGN is
effective in adapting pre-trained models to various new datasets: It surpasses
previous methods by a large margin on 12/12 datasets and even outperforms
full-finetuning on 5/12, while requiring 100x less parameters.

本论文介绍了一种基于视觉提示学习的模型适应方法，提出了 Prompt Generation Network (PGN) 网络，通过从端到端学习的词汇表中采样生成高性能、与输入相关的提示，从而使得预先训练的模型更适应不同的数据集。实验表明，PGN 在 12 个数据集上均优于以前的方法，并且在 5 个数据集上甚至优于全微调，而只需要 100 倍以下的参数。