Label-Free Foundational Model Selection for Medical Image Classification under Distribution Shift via Pseudo Label Discrepancy

• URL: http://arxiv.org/abs/2608.25810v1
• Date: Wed, 26 Aug 2026 13:56:29 GMT
• Title: Label-Free Foundational Model Selection for Medical Image Classification under Distribution Shift via Pseudo Label Discrepancy
• Abstract summary: We propose a label-free selection criterion built on SUDO, a framework for evaluating clinical AI systems without ground-truth annotations.<n>We show that AURCC can be used to rank a variety of vision-language models on chest X-ray classification.
• Score: 3.0016442487726884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models are increasingly deployed for medical image analysis. However, under the inter-institutional distribution shift typical of deployment, their performance varies widely and cannot be known without target-domain labels, which are rarely available. This leaves a practical question unresolved: given several candidate foundational models and labeled-data from a source domain, which one to deploy in an unlabeled target domain? We propose a label-free selection criterion built on SUDO, a framework for evaluating clinical AI systems without ground-truth annotations. SUDO partitions the unlabeled target data by predicted probability and, for each region, measures a pseudo-label discrepancy reflecting class contamination; aggregated across regions, this yields a score (AURCC) requiring neither target annotation nor fine-tuning. We show that AURCC can be used to rank a variety of vision-language models (BioMedCLIP, CXR-CLIP, CheXzero, MedCLIP, MedImageInsight, CLIP) on chest X-ray classification across three inter-hospital shift scenarios, under zero-shot and MLP-probe regimes. The AURCC ranking recovers the ground-truth ranking with Spearman rho up to 0.943 (p<0.05). Against the natural baseline of ranking by held-out source accuracy, AURCC is competitive when the labeled source is large and yields a more accurate ranking once it is small; the regime of interest in resource-constrained settings.

Related papers

• How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging [0.4893345190925178]
  unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship.<n>We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection.<n>Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators) evaluating over 80,000 trained models in total.
  arXiv  Detail & Related papers  (2026-08-12T13:19:14Z)
• Domain-Aware Hierarchical Contrastive Learning for Semi-Supervised Generalization Fault Diagnosis [49.89578655034085]
  We propose a unified framework termed domain-aware hierarchical contrastive learning (DAHCL) for fault diagnosis.<n>DAHCL captures source-domain geometric characteristics and calibrates pseudo-label predictions across heterogeneous source domains.<n>We also develop a hierarchical contrastive learning module that combines dynamic confidence stratification with fuzzy contrastive supervision.
  arXiv  Detail & Related papers  (2026-04-22T08:41:27Z)
• Labeled-to-Unlabeled Distribution Alignment for Partially-Supervised Multi-Organ Medical Image Segmentation [30.953837550398884]
  Partially-supervised multi-organ medical image segmentation aims to develop a unified semantic segmentation model. We propose a labeled-to-unlabeled distribution alignment framework that aligns feature distributions and enhances discriminative capability. Our method outperforms the state-of-the-art partially-supervised methods by a considerable margin.
  arXiv  Detail & Related papers  (2024-09-05T03:55:37Z)
• Scale Federated Learning for Label Set Mismatch in Medical Image Classification [4.344828846048128]
  Federated learning (FL) has been introduced to the healthcare domain as a decentralized learning paradigm. Most previous studies have assumed that every client holds an identical label set. We propose the framework FedLSM to solve the problem of Label Set Mismatch.
  arXiv  Detail & Related papers  (2023-04-14T05:32:01Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays [42.1336336144291]
  We propose to train the CXR abnormality localization framework via a weakly semi-supervised strategy, termed Point Beyond Class. The core idea behind our PBC is to learn a robust and accurate mapping from the point annotations to the bounding boxes. Experimental results on RSNA and VinDr-CXR datasets justify the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-09-05T14:36:07Z)
• Cycle Label-Consistent Networks for Unsupervised Domain Adaptation [57.29464116557734]
  Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. We propose a simple yet efficient domain adaptation method, i.e. Cycle Label-Consistent Network (CLCN), by exploiting the cycle consistency of classification label. We demonstrate the effectiveness of our approach on MNIST-USPS-SVHN, Office-31, Office-Home and Image CLEF-DA benchmarks.
  arXiv  Detail & Related papers  (2022-05-27T13:09:08Z)
• Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
  We introduce certainty-aware pseudo labels tailored for object detection. We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
  arXiv  Detail & Related papers  (2021-06-01T01:32:03Z)
• Learning Target Domain Specific Classifier for Partial Domain Adaptation [85.71584004185031]
  Unsupervised domain adaptation (UDA) aims at reducing the distribution discrepancy when transferring knowledge from a labeled source domain to an unlabeled target domain. This paper focuses on a more realistic UDA scenario, where the target label space is subsumed to the source label space.
  arXiv  Detail & Related papers  (2020-08-25T02:28:24Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)

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.