paper-with-me

Papers

Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models

2023-03-16 · Xinyang Liu, Dongsheng Wang, Bowei Fang, Miaoge Li, Zhibin Duan, Yishi Xu, Bo Chen, Mingyuan Zhou

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the prompt tuning as a point estimation problem, may fail to describe diverse characteristics of categories and limit their applications. We introduce a Bayesian probabilistic resolution to prompt tuning, where the label-specific stochastic prompts are generated hierarchically by first sampling a latent vector from an underlying distribution and then employing a lightweight generative model. Importantly, we semantically regularize the tuning process by minimizing the statistical distance between the visual patches and linguistic prompts, which pushes the stochastic label representations to faithfully capture diverse visual concepts, instead of overfitting the training categories. We evaluate the effectiveness of our approach on four tasks: few-shot image recognition, base-to-new generalization, dataset transfer learning, and domain shifts. Extensive results over 15 datasets show promising transferability and generalization performance of our proposed model, both quantitatively and qualitatively.

📄 PDF Abstract BibTeX arXiv:2303.09100

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt EngineeringTransfer Learning

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Prompt-aligned Gradient for Prompt Tuning

2022-05-30 · ICCV 2023 1 · Beier Zhu, Yulei Niu, Yucheng Han, Yue Wu 외

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e.g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided s…

Domain AdaptationFew-Shot LearningGeneral KnowledgeSentence

Craft: Cross-modal Aligned Features Improve Robustness of Prompt Tuning

2024-07-22 · Jingchen Sun, Rohan Sharma, Vishnu Suresh Lokhande, Changyou Chen

Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to l…

cross-modal alignment

Attention to Burstiness: Low-Rank Bilinear Prompt Tuning

2025-06-28 · Yuzhu Wang, Manni Duan, Shu Kong

Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts. In VPT, we uncover …

Visual Prompt Tuning

Understanding Prompt Tuning and In-Context Learning via Meta-Learning

2025-05-22 · Tim Genewein, Kevin Wenliang Li, Jordi Grau-Moya, Anian Ruoss 외

Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the literature. Method development is mainly em…

In-Context LearningMeta-Learning

PPOM: Marginalizing Patch-Grid Phase for CLIP-Based Generalizable Vision-Language Prompt Tuning

2026-08-14 · Liang Wang, Haoyang Li, Chao Wang, Guodong Long 외 arxiv

Prompt tuning adapts CLIP-based vision-language models with few trainable parameters, yet its predictions remain sensitive to the spatial sampling imposed by a frozen vision transformer. In particular, non-overlapping pa…