Prompt Distribution Matters: Tuning Visual Prompt Through Semantic Metric Guidance
Keywords: visual prompt tuning, parameter-efficient fine-tuning, metric learning
TL;DR: We propose a novel framework to guide visual prompts for PEFT
Abstract: Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformer (ViT) models on downstream vision tasks. VPT partially fine-tunes a set of learnable tokens while keeping the majority of the model parameters frozen. Recent research has explored modifying the connection structures of the prompts. However, the fundamental correlation and distribution between the prompts and image tokens remain unexplored. In this paper, we leverage \textit{metric learning} techniques to investigate how the distribution of prompts affects fine-tuning and transfer learning performance. Specifically, we propose a novel framework, \textbf{D}istribution \textbf{A}ware \textbf{V}isual \textbf{P}rompt Tuning (DA-VPT), to guide the distributions of the prompts by learning the distance metric from their class-related semantic data. Our method demonstrates that the prompts can serve as an effective bridge to share semantic information between image patches and the class token. We extensively evaluated our approach on popular benchmarks in both recognition and segmentation tasks. The results show the effectiveness of our proposed method and offer a new direction for PEFT optimization in vision transformers. We demonstrate that our approach enables more effective and efficient fine-tuning of ViT models by leveraging semantic information to guide the learning of the prompts, leading to improved performance on various downstream vision tasks.
Primary Area: transfer learning, meta learning, and lifelong learning
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: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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.
Submission Number: 3380
Loading