Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation

• URL: http://arxiv.org/abs/2602.05937v1
• Date: Thu, 05 Feb 2026 17:47:35 GMT
• Title: Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation
• Authors: Lingrui Li, Yanfeng Zhou, Nan Pu, Xin Chen, Zhun Zhong,
• Abstract summary: Distribution shift is a common challenge in medical images obtained from different clinical centers.<n>Continual Test-Time Adaptation has emerged as a promising approach to address cross-domain shifts.
• Score: 45.41333594408632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Distribution shift is a common challenge in medical images obtained from different clinical centers, significantly hindering the deployment of pre-trained semantic segmentation models in real-world applications across multiple domains. Continual Test-Time Adaptation(CTTA) has emerged as a promising approach to address cross-domain shifts during continually evolving target domains. Most existing CTTA methods rely on incrementally updating model parameters, which inevitably suffer from error accumulation and catastrophic forgetting, especially in long-term adaptation. Recent prompt-tuning-based works have shown potential to mitigate the two issues above by updating only visual prompts. While these approaches have demonstrated promising performance, several limitations remain:1)lacking multi-scale prompt diversity, 2)inadequate incorporation of instance-specific knowledge, and 3)risk of privacy leakage. To overcome these limitations, we propose Multi-scale Global-Instance Prompt Tuning(MGIPT), to enhance scale diversity of prompts and capture both global- and instance-level knowledge for robust CTTA. Specifically, MGIPT consists of an Adaptive-scale Instance Prompt(AIP) and a Multi-scale Global-level Prompt(MGP). AIP dynamically learns lightweight and instance-specific prompts to mitigate error accumulation with adaptive optimal-scale selection mechanism. MGP captures domain-level knowledge across different scales to ensure robust adaptation with anti-forgetting capabilities. These complementary components are combined through a weighted ensemble approach, enabling effective dual-level adaptation that integrates both global and local information. Extensive experiments on medical image segmentation benchmarks demonstrate that our MGIPT outperforms state-of-the-art methods, achieving robust adaptation across continually changing target domains.

Related papers

• Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation [84.97054460338109]
  Cross-Domain Few-Shot aims to segment in data-scarce domains conditioned on a few exemplars.<n>We propose Multi-view Progressive Adaptation, which progressively adapts few-shot capability to target domains from both data and strategy perspectives.<n> MPA effectively adapts few-shot capability to target domains, outperforming state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2026-02-05T02:16:44Z)
• Instance-Aware Test-Time Segmentation for Continual Domain Shifts [19.919913865727995]
  Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains.<n>We propose an approach that adaptively adjusts pseudo labels to reflect the confidence distribution within each image.<n>This fine-grained, class- and instance-aware adaptation produces more reliable supervision and mitigates error accumulation.
  arXiv  Detail & Related papers  (2025-12-09T13:06:15Z)
• The 1st Solution for CARE Liver Task Challenge 2025: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation [23.156209918252838]
  CoSSeg-TTA is a compact segmentation framework for the GED4 (Gd-EOB-DTPA enhanced hepatobiliary phase MRI) modality built upon nnU-Netv2.<n>A domain adaptation module, incorporating a randomized histogram-based style appearance transfer function and a trainable contrast-aware network, enriches domain diversity and mitigates cross-center variability.
  arXiv  Detail & Related papers  (2025-10-05T15:18:53Z)
• Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation [17.49123106322442]
  Test-time adaptation (TTA) adjusts a learned model using unlabeled test data.<n>We incorporate morphological information and propose a framework based on multi-graph matching.<n>Our method outperforms other state-of-the-art approaches on two medical image segmentation benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T10:11:11Z)
• Test-Time Modality Generalization for Medical Image Segmentation [0.9092907230570326]
  Generalizable medical image segmentation is essential for ensuring consistent performance across diverse unseen clinical settings.<n>We introduce a novel Test-Time Modality Generalization (TTMG) framework, which comprises two core components: Modality-Aware Style Projection (MASP) and Modality-Sensitive Instance Whitening (MSIW)<n>MASP estimates the likelihood of a test instance belonging to each seen modality and maps it onto a distribution using modality-specific style bases, guiding its projection effectively.<n>MSIW is applied during training to selectively suppress modality-sensitive information while retaining modality-invariant features.
  arXiv  Detail & Related papers  (2025-02-27T01:32:13Z)
• FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation [19.87797382888023]
  Medical image segmentation is challenging due to the diversity of medical images and the lack of labeled data.<n>We present a novel framework, Federated Generalization-Aware SemiSupervised Learning (FGASL), to address the challenges in FedSemiDG.<n>Our method significantly outperforms state-of-the-art FSSL and domain generalization approaches, achieving robust generalization on unseen domains.
  arXiv  Detail & Related papers  (2025-01-13T14:54:49Z)
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation [48.039156140237615]
  A Continual Test-Time Adaptation task is proposed to adapt the pre-trained model to continually changing target domains. We design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-06-07T11:18:53Z)
• Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters [59.82088750033897]
  We set up a Generalized FSCL (GFSCL) protocol involving both class- and domain-incremental situations. We find that common continual learning methods have poor generalization ability on unseen domains. In this way, we propose a rehearsal-free framework based on Vision Transformer (ViT) named Contrastive Mixture of Adapters (CMoA)
  arXiv  Detail & Related papers  (2023-02-12T15:18:14Z)
• Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment [59.831917206058435]
  Domain adaptive detection aims to improve the generalization of detectors on target domain. Recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. We introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning.
  arXiv  Detail & Related papers  (2023-01-01T08:38:07Z)
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains [68.73614619875814]
  We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation. Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.
  arXiv  Detail & Related papers  (2020-07-04T07:56:02Z)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.