Read-only Prompt Optimization for Vision-Language Few-shot Learning

Dongjun Lee, Seokwon Song, Jihee Suh, Joonmyeong Choi, Sanghyeok Lee, Hyunwoo J. Kim; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 1401-1411

In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to down- stream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre- trained weights frozen. However, learnable prompts can affect the internal representation within the self-attention module, which may negatively impact performance vari- ance and generalization, especially in data-deficient set- tings. To address these issues, we propose a novel ap- proach, Read-only Prompt Optimization (RPO). RPO lever- ages masked attention to prevent the internal representa- tion shift in the pre-trained model. Further, to facilitate the optimization of RPO, the read-only prompts are ini- tialized based on special tokens of the pre-trained model. Our extensive experiments demonstrate that RPO outper- forms CLIP and CoCoOp in base-to-new generalization and domain generalization while displaying better robust- ness. Also, the proposed method achieves better generaliza- tion on extremely data-deficient settings, while improving parameter efficiency and computational overhead. Code is available at https://github.com/mlvlab/RPO.