Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation
Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire network, making it both computationally expensive and challenging, particularly when coupled with min-max objectives. Inspired by recent advances in prompt learning that adapts high-capacity models for downstream tasks in a computationally economic way, we introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. Given a source and target domain pair, MPA first trains an individual prompt to minimize the domain gap through a contrastive loss. Then, MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Moreover, we show that the resulting subspace acquired from the auto-encoding process can easily generalize to a streamlined set of target domains, making our method more efficient for practical usage. Extensive experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet.
Code (1)
Tasks
Domain AdaptationMulti-Source Unsupervised Domain AdaptationPrompt LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. …
Domain AdaptationPrompt EngineeringPrompt LearningUnsupervised Domain AdaptationMulti-Prompt Progressive Alignment for Multi-Source Unsupervised Domain Adaptation
Large Vision-Language Models like CLIP have become a powerful foundation for Unsupervised Domain Adaptation due to their strong zero-shot generalization. State-of-the-art methods typically leverage CLIP to generate pseud…
Unsupervised Domain AdaptationZero-shot GeneralizationC-DGPA: Class-Centric Dual-Alignment Generative Prompt Adaptation
Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi…
Unsupervised Domain AdaptationEnhancing Domain Adaptation through Prompt Gradient Alignment
Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works b…
Domain AdaptationLanguage ModelingLanguage ModellingMulti-Source Unsupervised Domain Adaptation+2ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation
The domain discrepancy existed between medical images acquired in different situations renders a major hurdle in deploying pre-trained medical image segmentation models for clinical use. Since it is less possible to dist…
Domain AdaptationImage SegmentationMedical Image SegmentationPrompt Learning+5