Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning

TL;DR

This paper introduces DiffTPT, a novel test-time prompt tuning method that uses pre-trained diffusion models to generate diverse data, enhancing adaptation to unseen domains and improving zero-shot accuracy in vision-language models.

Contribution

The paper proposes DiffTPT, which leverages diffusion models for diverse data augmentation and introduces a cosine similarity filter to improve test-time prompt tuning.

Findings

DiffTPT achieves an average 5.13% improvement in zero-shot accuracy.

Incorporates both conventional and diffusion-based data augmentation.

Uses cosine similarity filtering to select high-fidelity generated data.

Abstract

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 the single test sample. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13\% compared to the state-of-the-art TPT method. Our code and models will be publicly released.