FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation

TL;DR

This paper introduces Fourier Visual Prompting (FVP), a novel method for source-free unsupervised domain adaptation in medical image segmentation, which improves performance by adding learnable visual prompts to frozen pre-trained models.

Contribution

FVP is the first to apply visual prompts to SFUDA in medical image segmentation, using low-frequency learnable parameters to adapt frozen models without source data.

Findings

FVP outperforms existing methods on three public datasets.

FVP effectively adapts frozen models to target domains.

FVP requires only a small number of learnable parameters.

Abstract

Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.