Soft Prompt Generation for Domain Generalization

TL;DR

This paper introduces Soft Prompt Generation (SPG), a generative approach to create diverse, domain-specific prompts for vision-language models, significantly improving domain generalization performance across multiple benchmarks.

Contribution

The paper proposes a novel generative framework for soft prompt learning that enhances diversity and domain adaptation in vision-language models for domain generalization.

Findings

SPG achieves state-of-the-art results on five DG benchmarks.

The method effectively generates instance-specific prompts for unseen domains.

Extensive experiments validate the superiority of SPG over existing prompt learning methods.

Abstract

Large pre-trained vision language models (VLMs) have shown impressive zero-shot ability on downstream tasks with manually designed prompt. To further adapt VLMs to downstream tasks, soft prompt is proposed to replace manually designed prompt, which undergoes fine-tuning based on specific domain data. Prior prompt learning methods primarily learn a fixed prompt or residuled prompt from training samples. However, the learned prompts lack diversity and ignore information about unseen domains. In this paper, we reframe the prompt learning framework from a generative perspective and propose a simple yet efficient method for the Domain Generalization (DG) task, namely Soft Prompt Generation (SPG). Specifically, SPG consists of a two-stage training phase and an inference phase. During the training phase, we introduce soft prompt label for each domain, aiming to incorporate the generative model domain knowledge. During the inference phase, the generator of the generative model is employed to obtain instance-specific soft prompts for the unseen target domain. Extensive experiments on five domain generalization benchmarks of three DG tasks demonstrate that SPG achieves state-of-the-art performance. The code is available at https://github.com/renytek13/Soft-Prompt-Generation-with-CGAN.