paper-with-me

Papers

Visual Instance-aware Prompt Tuning

2025-07-10 · Xi Xiao, Yunbei Zhang, Xingjian Li, Tianyang Wang, Xiao Wang, Yuxiang Wei, Jihun Hamm, Min Xu arxiv

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this strategy results in sub-optimal performance due to high variance in downstream datasets. To address this challenge, we propose Visual Instance-aware Prompt Tuning (ViaPT), which generates instance-aware prompts based on each individual input and fuses them with dataset-level prompts, leveraging Principal Component Analysis (PCA) to retain important prompting information. Moreover, we reveal that VPT-Deep and VPT-Shallow represent two corner cases based on a conceptual understanding, in which they fail to effectively capture instance-specific information, while random dimension reduction on prompts only yields performance between the two extremes. Instead, ViaPT overcomes these limitations by balancing dataset-level and instance-level knowledge, while reducing the amount of learnable parameters compared to VPT-Deep. Extensive experiments across 34 diverse datasets demonstrate that our method consistently outperforms state-of-the-art baselines, establishing a new paradigm for analyzing and optimizing visual prompts for vision transformers.

📄 PDF Abstract BibTeX arXiv:2507.07796

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningVisual Prompt Tuning

Similar Papers 제목 키워드 기반

Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model

2022-08-17 · Yinghui Xing, Qirui Wu, De Cheng, Shizhou Zhang 외

With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial infor…

General KnowledgeLanguage ModellingVisual Prompt Tuning

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

2023-04-14 · ICCV 2023 1 · Yaohua Zha, Jinpeng Wang, Tao Dai, Bin Chen 외

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads …

3D Parameter-Efficient Fine-Tuning for Classification3D Point Cloud ClassificationFew-Shot 3D Point Cloud ClassificationVisual Prompt Tuning

All You Need is One: Capsule Prompt Tuning with a Single Vector

2025-10-19 · Yiyang Liu, James C. Liang, Heng Fan, Wenhao Yang 외 arxiv

Prompt-based learning has emerged as a parameter-efficient finetuning (PEFT) approach to facilitate Large Language Model (LLM) adaptation to downstream tasks by conditioning generation with task-aware guidance. Despite i…

SEP: Self-Enhanced Prompt Tuning for Visual-Language Model

2024-05-24 · Hantao Yao, Rui Zhang, Lu Yu, Yongdong Zhang 외

Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as th…

Language ModelingLanguage Modelling

VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models

2025-11-27 · Silin Cheng, Kai Han arxiv

Vision-language models (VLMs), such as CLIP, have shown strong generalization under zero-shot settings, yet adapting them to downstream tasks with limited supervision remains a significant challenge. Existing multi-modal…

Representation LearningDomain Generalization