Can I read Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning on EtoBox?

Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning by Feng, Chun-Mei; Yu, Kai; Liu, Yong; Khan, Salman; Zuo, Wangmeng is a scholarly article available to read on EtoBox.

What is Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning about?

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive prompts on the fly for each test sample from an unseen new domain, which is known as test-time prompt tuning (TPT). Existing TPT methods typically rely on data augmentation and confidence selection. However, conventional data augmentation techniques, e.g., random resized crops, suffers from the lack of data diversity, while entropy-based confidence selection alone is not sufficient to guarantee prediction fidelity. To address these issues, we propose a novel TPT method, named DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Specifically, we incorporate augmented data by both conventional method and pre-trained stable diffusion to exploit their respective merits, improving the models ability to adapt to unknown new test data. Moreover, to ensure the prediction fidelity of generated data, we introduce a cosine similarity-based filtration technique to select the generated data with higher similarity to

Author

Feng, Chun-Mei; Yu, Kai; Liu, Yong; Khan, Salman; Zuo, Wangmeng

Published

2023

Language

EN