cs.CVFeb 23, 2026

Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

Authors: Jiabao Chen, Shan Xiong, Jialin Peng

Organizations: College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent unsupervised domain adaptation (UDA) strategies often demonstrate limited and biased performance, which hinders their practical applications. In this study, we explore sparse points and local human preferences as weak labels in the target domain, thereby presenting a more realistic yet annotation-efficient setting. Specifically, we develop Prefer-DAS, which pioneers sparse promptable learning and local preference alignment. The Prefer-DAS is a promptable multitask model that integrates self-training and prompt-guided contrastive learning. Unlike SAM-like methods, the Prefer-DAS allows for the use of full, partial, and even no point prompts during both training and inference stages and thus enables interactive segmentation. Instead of using image-level human preference alignment for segmentation, we introduce Local direct Preference Optimization (LPO), plug-and-play solutions for alignment with spatially varying human feedback. To address potential missing feedback, we also introduce Unsupervised Preference Optimization (UPO), which leverages self-learned preferences. As a result, the Prefer-DAS model can effectively perform both weakly-supervised and unsupervised DAS, depending on the availability of points and human preferences. Comprehensive experiments on four challenging DAS tasks demonstrate that our model outperforms SAM-like methods as well as unsupervised and weakly-supervised DAS methods in both automatic and interactive segmentation modes, highlighting strong generalizability and flexibility. Additionally, the performance of our model is very close to or even exceeds that of supervised models.

Figures & tables

Fig. 1: A visualization of local human preferences. While selecting preferred segmentation at the image level usually poses challenges for human raters and results in reward misspecification in preference optimization, we gather local preferences at the patch level. Here, an image of small size and 2 ×\times 2 patches are used solely for illustrative purposes.
Fig. 2: Illustration of our Prefer-DAS model for weakly-supervised domain adaptive segmentation. Our framework comprises two stages. The first stage performs promptable domain-adaptive segmentation for UDA or WDA segmentation, depending on the availability of sparse points; the second stage performs locally supervised or unsupervised preference learning, depending on the availability of human preferences.
TypesMethodsTraining H →\rightarrow R R →\rightarrow H H →\rightarrow Lucchi++ H →\rightarrow Stem
Point Prompts DiceAJIPQ DiceAJIPQ DiceAJIPQ DiceAJIPQ
Automatic Segmentation Mode     
SAM-likeSAM [ 2 ]0% 32.014.330.0 20.811.418.7 21.510.311.3 19.00.90.3
SAM-Med2D [ 9 ] 15.9-- 22.5-- 23.112.72.6 27.913.03.3
Med-SAM Adapter [ 10 ] † 75.556.627.5 72.455.033.4 64.644.819.5 27.812.97.1
UDAUALR [ 18 ]0% 86.371.653.7 83.869.760.0 81.368.163.2 65.538.728.7
TABLE I: Quantitative comparison. Leading UDA, WDA, and SAM-like approaches in both automatic and interactive modes are compared. Our Prefer-DAS is flexible to conduct both UDA and WDA, depending on the availability of the training point prompts and human preferences, and can utilize sparse point prompts during inference. For interactive segmentation, indicated by a ”+”, full center points for all mitochondria are used as testing prompts to fulfill the requirements of SAM-like methods.
Fig. 3: Visual comparison of segmentation results in both automatic and interactive modes. Despite the Med-SAM Adapter+ and WeSAM+ being fine-tuned with the source EM data and utilizing full point prompts during inference, they still show severe false positive segmentation.
 Pseudo-labelingTrainingPCLLPO H →\rightarrow R R →\rightarrow H
 Det.Seg.Prompts DicePQ DicePQ
I      88.668.7 78.155.5
II✓     89.270.4 87.468.4
III ✓    89.570.0 87.768.3
IV✓✓    90.471.8 88.568.8
V✓✓✓   92.774.1 88.969.0
TABLE II: Ablation study of the proposed model.
Fig. 4: Box plot of our Prefer-DAS using different DPOs. Global and local refer to image-level and patch-level preferences, respectively. ”w/o” indicates the Prefer-DAS using no preferences.
Fig. 5: Qualitative comparison of different strategies for preference learning. GPO refers to learning using image-level human preferences.
DPONegative(s) H →\rightarrow R R →\rightarrow H H →\rightarrow Lucchi++
SingleMultiple DicePQ DicePQ DicePQ
GPO✓  94.078.2 91.173.3 93.280.5
 ✓ 94.378.7 91.574.2 93.481.7
LPO✓  94.278.0 91.374.7 93.982.3
 ✓ 94.679.6 92.275.8 94.182.3
TABLE III: Effectiveness of using multiple negatives.
Fig. 6: Effectiveness of preference learning in correcting defective and biased segmentation. Red: Ground truth; Cyan: CAFA; Blue: Prompt-DAS; Yellow: Prefer-DAS (UPO); Green: Prefer-DAS (LPO). The H →\rightarrow Lucchi++ task is used for evaluation. Both CAFA and Prompt-DAS reveal two types of segmentation defects: 1) incomplete segmentation and 2) misalignment with target annotations, which primarily arises from the domain inconsistency in annotating inner and outer membrane edges.
ModelTestingH →\rightarrow R R →\rightarrow H H →\rightarrow Lucchi++
PromptsDicePQ DicePQ DicePQ
Prompt-DAS0%93.374.5 89.269.1 88.273.7
15%93.574.2 90.069.8 88.674.7
50%93.574.2 90.470.9 88.674.8
100%93.574.2 90.872.3 88.774.8
 0%93.777.5 90.171.2 92.680.9
TABLE IV: Influence of the quantity of inference point prompts on interactive segmentation. Different from SAM, our models can utilize partial point prompts.
More in this topic

Domain Adaptation

Domain adaptation transfers machine-learning models across changing data distributions, often using unlabeled or limited target-domain examples.

See all 252 papers

Explore similar work

CardsList
Sep 28, 2026

Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement

Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. However, OVSS performance often degrades in specialized domains such as medical imaging, remote sensing, and industrial inspection, where dense pixel-level masks for adaptation are costly to obtain and require domain-specific expertise. We propose a preference-guided adaptation framework that replaces dense mask supervision with binary preferences. We observe that different prompt templates produce systematically different segmentations for the same image, a phenomenon we call prompt disagreement, and we repurpose it as a built-in source of preference supervision. Building on this, we mine localized preference queries from regions of high cross-template uncertainty, and adapt the OVSS model with Region-Localized Preference Optimization (RLPO) together with consistency regularization that stabilizes updates outside the queried region. Across extensive experiments on the MESS benchmark, the proposed method achieves consistent gains across diverse OVSS backbones without any pixel-level annotation, and remains effective under noisy preferences. Our code is available at https://github.com/blue-531/pref-ovss.

Hyun-Kurl Jang, Jihun Kim, Kuk-Jin Yoon

Visual Intelligence Lab. KAIST

Weakly Supervised Semantic SegmentationPreference OptimizationOpen-Vocabulary Semantic Segmentation
AskPDF
Jun 19, 2026

μμMatch: Foundation Models for Semi-supervised Learning and Domain Adaptation in EM

Vision foundation models have substantially advanced computer vision, enabling state-of-the-art performance in zero- and few-shot settings. They have been successfully applied to biomedical imaging tasks ranging from organ segmentation in computed tomography to cell segmentation in light microscopy. Electron microscopy (EM) is a central modality for analyzing cellular ultrastructure due to its nanometer-scale resolution. However, the application of foundation models in EM has so far been limited to specific organelles, such as mitochondria, largely due to the diversity of segmentation tasks and the scarcity of comprehensively annotated data. As a result, EM segmentation still predominantly relies on supervised learning, requiring extensive manual annotation and limiting ultrastructural analysis. To address this gap, we propose μμMatch, a framework for semi-supervised learning and domain adaptation that leverages foundation models. We implement state-of-the-art student-teacher-based methods and evaluate multiple foundation models (SAM, SAM2, μμSAM, DINOv2/v3) on challenging EM tasks, including mitochondrion, nucleus, and neurite segmentation. Our results demonstrate consistent improvements over strong baselines and highlight a path toward substantially reducing the annotation effort in EM.

Marei Freitag, Olesia Korchevaia, Luca Freckmann +2

Life and Medical Sciences Institute (LIMES), University of Bonn, Germany · Institute of Computer Science, Georg-August-University Göttingen, Germany

Electron MicroscopyUnsupervised Domain AdaptationVision Foundation Model AdaptationSemi-Supervised Medical Image SegmentationMicroscopy Image Analysis
AskPDF
Mar 5, 2026

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model

Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods are typically designed for low-gap, specific domain shifts and cannot generalize into a unified, multi-modalities, and multi-target framework, which presents a major barrier to real-world application. To overcome this issue, we introduce Tell2Adapt, a novel SFUDA framework that harnesses the vast, generalizable knowledge of the Vision Foundation Model (VFM). Our approach ensures high-fidelity VFM prompts through Context-Aware Prompts Regularization (CAPR), which robustly translates varied text prompts into canonical instructions. This enables the generation of high-quality pseudo-labels for efficiently adapting the lightweight student model to target domain. To guarantee clinical reliability, the framework incorporates Visual Plausibility Refinement (VPR), which leverages the VFM's anatomical knowledge to re-ground the adapted model's predictions in target image's low-level visual features, effectively removing noise and false positives. We conduct one of the most extensive SFUDA evaluations to date, validating our framework across 10 domain adaptation directions and 22 anatomical targets, including brain, cardiac, polyp, and abdominal targets. Our results demonstrate that Tell2Adapt consistently outperforms existing approaches, achieving SOTA for a unified SFUDA framework in medical image segmentation. Code are avaliable at https://github.com/derekshiii/Tell2Adapt.

Yulong Shi, Shijie Li, Ziyi Li +1

College of Medicine and Biological Information Engineering, Northeastern University · Engineering Research Center of Medical Imaging and Intelligent Analysis, Ministry of Education · Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University

Source-Free Domain AdaptationMedical Image SegmentationVision Foundation Model Adaptation
AskPDF