Prompt Generation Networks for Efficient Adaptation of Frozen Vision Transformers

Jochem Loedeman, Maarten Stol, Tengda Han, Yuki M Asano

Keywords: model adaptation, pretrained models, prompting, vision transformers

Abstract: Large-scale pretrained models, especially those trained from vision-language data have demonstrated the tremendous value that can be gained from both larger training datasets and models. Thus, in order to benefit from these developments, there is renewed interest in transfer learning and adapting models from large-scale general pretraining to particular downstream tasks. However, the continuously increasing size of the models means that even the classic approach of finetuning is becoming infeasible for all but big institutions. Prompt learning has emerged as a flexible way to adapt models by solely learning additional inputs to a model that is kept frozen, but so far performances remained inferior to finetuning. To address this, we propose the Prompt Generation Network (PGN) that generates input-dependent prompts by sampling from a learned library of tokens. We show the PGN is effective in adapting pretrained models to various new datasets. It surpasses previous prompt-learning methods by a large margin and even full-finetuning on 5 out of 12 datasets while requiring 100x less parameters. PGN can even be used for training and inferring on multiple datasets simultaneously and learns to allocate tokens between domains. Given these findings, we conclude that PGN is a viable and scalable approach for downstream adaptation of frozen models.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: A novel method for adapting frozen pretrained vision transformer models by adding prompts that vary based on each input, which can surpass even full-finetuning.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/prompt-generation-networks-for-efficient/code)