Concept Alignment Contrast and Long-Short Prompt Memory for Test-Time Adaptation of SAM3 in Medical Image Segmentation

• URL: http://arxiv.org/abs/2606.22963v2
• Date: Wed, 01 Jul 2026 07:02:05 GMT
• Title: Concept Alignment Contrast and Long-Short Prompt Memory for Test-Time Adaptation of SAM3 in Medical Image Segmentation
• Abstract summary: Test-Time Adaptation (TTA) is essential for improving the testing performance by updating the model on the fly without annotations.<n>Existing vision-language TTA methods are mainly driven by image-level uncertainty minimization.<n>We propose Concept Alignment Contrast and LongShort Prompt Memory for Test-Time Adaptation (CM-TTA) of SAM3 for medical images.
• Score: 14.712933368175008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept segmentation models like Segment Anything Model 3 (SAM3) show strong generalization on natural images, yet their performance degrades in medical imaging due to the domain gap caused by different imaging principles and styles. Test-Time Adaptation (TTA) is essential for improving the testing performance by updating the model on the fly without annotations. However, existing vision-language TTA methods are mainly driven by image-level uncertainty minimization, which does not necessarily reflect region-level semantic correctness in medical segmentation. Moreover, they often lack mechanisms to maintain stability in continual one-pass adaptation, leading to limited performance when reliable dense supervision is missing for segmentation. To address these issues, we propose Concept Alignment Contrast and LongShort Prompt Memory for Test-Time Adaptation (CM-TTA) of SAM3 for medical images. First, for a test sample with multiple augmentations, we introduce a novel Concept Alignment Contrast (CAC) metric, which leverages textual-visual semantic consistency to robustly evaluate prediction quality to select the best augmented view as the supervision. Second, to balance rapid and stable adaptation, we design a Long-Short Prompt Memory (LSPM) module. The short memory dynamically fuses recent prompts based on CAC scores for agile local adaptation, while the long memory maintains a stable global prompt to generate enhanced pseudo-labels. Finally, a Densely Supervised Prompt Update (DSPU) strategy is proposed to optimize the prompt embeddings with enhanced pseudo labels as dense supervision. Extensive experiments on prostate and skin lesion segmentation demonstrate that our CM-TTA framework significantly outperforms existing methods for TTA of SAM3. The code is available at https://github.com/SherlockZYB/CM-TTA.

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection [52.986874008247554]
  We propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes.<n>ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation.<n>It achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets.
  arXiv  Detail & Related papers  (2026-08-01T04:46:55Z)
• Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation [45.4173998742666]
  Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time.<n>We propose Memory-Supported Synergistic Adaptation (MSSA), a novel training-free TTA framework for medical image segmentation.
  arXiv  Detail & Related papers  (2026-07-20T08:41:47Z)
• AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis [57.942670844512016]
  We introduce AdaSurvMamba as a novel adaptive framework for multimodal survival analysis.<n>The framework features a Dual-Scale Importance-Aware Reconstruction (DSIR) module to dynamically modulate cross-modal interaction strength.<n>Experiments across five TCGA cohorts demonstrate consistent gains over existing methods.
  arXiv  Detail & Related papers  (2026-06-28T11:36:31Z)
• Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation [15.034102800030217]
  Mask to Concept (M2C) is an efficient framework that adapts SAM3 for medical few-shot annotation without external modules.<n>M2C searches for transferable visual concepts entirely within its frozen architecture.<n>Experiments on medical segmentation benchmarks show that our method achieves SOTA few-shot segmentation performance and outstanding annotation efficiency.
  arXiv  Detail & Related papers  (2026-06-25T07:44:37Z)
• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models [76.92890872338235]
  Large-scale pre-trained Vision-Language models (VLMs) exhibit strong zero-shot generalization, yet are highly vulnerable to imperceptible adversarial perturbations.<n>To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense.
  arXiv  Detail & Related papers  (2026-05-17T18:07:08Z)
• Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification [59.24009931000134]
  Multi-View Synergistic Learning (MVSL) is a unified framework that addresses adaptation paradigms, representation granularity, and disease semantic relationships.<n>MVSL decouples the adaptation of visual and textual encoders to respect their distinct representational characteristics.<n>It further introduces multi-granularity contrastive learning to explicitly model both global image semantics and localized lesion-level evidence.<n>MVSL consistently outperforms state-of-the-art methods in few-shot and zero-shot classification settings.
  arXiv  Detail & Related papers  (2026-04-27T02:41:27Z)
• Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study [6.850135803678454]
  We present a systematic evaluation of Segment Anything Model 3 (SAM3) for lesion segmentation.<n>Experiments on 13 datasets covering 11 lesion types demonstrate that SAM3 achieves strong cross-modality generalization.<n>These results highlight the potential of concept-based foundation models for scalable and practical medical image segmentation.
  arXiv  Detail & Related papers  (2026-03-26T22:30:10Z)
• SPEGC: Continual Test-Time Adaptation via Semantic-Prompt-Enhanced Graph Clustering for Medical Image Segmentation [12.0982298854338]
  Continual Test-Time Adaptation (CTTA) aims to enable pre-trained models to adapt to continuously changing unlabeled domains.<n>We propose a CTTA via Semantic-Prompt-Enhanced Graph Clustering (SPEGC) for medical image segmentation.
  arXiv  Detail & Related papers  (2026-03-12T03:22:43Z)
• BALR-SAM: Boundary-Aware Low-Rank Adaptation of SAM for Resource-Efficient Medical Image Segmentation [11.634558989215392]
  Vision foundation models like the Segment Anything Model (SAM) often struggle in medical image segmentation due to a lack of domain-specific adaptation.<n>We propose BALR-SAM, a boundary-aware low-rank adaptation framework that enhances SAM for medical imaging.<n>It combines three tailored components: (1) a Complementary Detail Enhancement Network (CDEN) using depthwise separable convolutions and multi-scale fusion to capture boundary-sensitive features essential for accurate segmentation; (2) low-rank adapters integrated into SAM's Vision Transformer blocks to optimize feature representation and attention for medical contexts, while simultaneously significantly reducing the parameter space; and
  arXiv  Detail & Related papers  (2025-09-29T02:36:09Z)
• TABNet: A Triplet Augmentation Self-Recovery Framework with Boundary-Aware Pseudo-Labels for Medical Image Segmentation [4.034121387622003]
  We propose TAB Net, a novel weakly-supervised medical image segmentation framework.<n>It consists of the triplet augmentation self-recovery (TAS) module and the boundary-aware pseudo-label supervision (BAP) module.<n>We show that TAB Net significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation.
  arXiv  Detail & Related papers  (2025-07-03T07:50:00Z)
• SSAM: Self-Supervised Association Modeling for Test-Time Adaption [42.00379819876794]
  We propose SSAM (Self-Supervised Association Modeling), a new TTA framework that enables dynamic encoder refinement through dual-phase association learning.<n>Our method operates via two synergistic components: 1) Soft Prototype Estimation (SPE), which estimates probabilistic category associations to guide feature space reorganization, and 2) Prototype-anchored Image Reconstruction (PIR), enforcing encoder stability through cluster-conditional image feature reconstruction.
  arXiv  Detail & Related papers  (2025-05-31T11:13:07Z)
• PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation [51.509573838103854]
  We propose a semi-supervised learning framework, termed Progressive Mean Teachers (PMT), for medical image segmentation. Our PMT generates high-fidelity pseudo labels by learning robust and diverse features in the training process. Experimental results on two datasets with different modalities, i.e., CT and MRI, demonstrate that our method outperforms the state-of-the-art medical image segmentation approaches.
  arXiv  Detail & Related papers  (2024-09-08T15:02:25Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)

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.