Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity

• URL: http://arxiv.org/abs/2608.17983v1
• Date: Tue, 18 Aug 2026 16:31:08 GMT
• Title: Dual Co-Train: Cross-Dataset Ultrasound Tongue Segmentation Under Extreme Data Scarcity
• Abstract summary: We present a source-free domain adaptation framework for robust ultrasound tongue segmentation built on a lightweight UltraUNet backbone.<n>The proposed method adapts to a fully-unlabeled target domain by iteratively refining pseudo-labels, filtering unreliable masks with a contour-based quality-control module, and generating target-style synthetic image-mask pairs.<n>We evaluate the method on 12 source-target transfer pairs across eight ultrasound tongue imaging datasets, and conduct source-size scaling experiments and ablation studies.
• Score: 7.853882738557613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ultrasound tongue contour segmentation remains challenging under cross-dataset domain shift, where limited annotations, probe variability, and acquisition noise often degrade model generalization. We present a source-free domain adaptation framework for robust ultrasound tongue segmentation built on a lightweight UltraUNet backbone. Starting from a checkpoint pretrained on only five labeled source images, simulating an underfitted constrained source model, the proposed method adapts to a fully-unlabeled target domain by iteratively refining pseudo-labels, filtering unreliable masks with a contour-based quality-control module, and generating target-style synthetic image-mask pairs through a segmentation-guided conditional GAN. The student model is then trained on a mixture of clean pseudo-labeled target images, noisy pseudo-labels with consistency regularization, and synthetic samples, enabling closed-loop adaptation without access to source data. We evaluate the method on 12 source-target transfer pairs across eight ultrasound tongue imaging datasets, and conduct source-size scaling experiments and ablation studies. Across all comparisons, the proposed framework improves segmentation overlap and contour accuracy over the baselines, including supervised ones. These results suggest that task-specific pseudo-label refinement and synthetic target-style augmentation can substantially improve source-free adaptation for ultrasound tongue imaging.

Related papers

• SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation [0.8717253904965373]
  Source-free unsupervised domain adaptation (SFUDA) adapts a pretrained model to an unlabeled target domain without requiring access to sensitive source data.<n>We introduce a novel SFUDA framework built on Symmetrical Flow Matching.<n>We evaluate on abdominal multi-organ and cardiac segmentation, covering cross-modality MRI->CT shifts, and multi-site prostate segmentation.
  arXiv  Detail & Related papers  (2026-08-23T18:09:39Z)
• Combating Noisy Labels through Fostering Self- and Neighbor-Consistency [120.4394402099635]
  Label noise is pervasive in various real-world scenarios, posing challenges in supervised deep learning.<n>We propose a noise-robust method named Jo-SNC (textbfJoint sample selection and model regularization based on textbfSelf- and textbfNeighbor-textbfConsistency)<n>We design a self-adaptive, data-driven thresholding scheme to adjust per-class selection thresholds.
  arXiv  Detail & Related papers  (2026-01-19T07:55:29Z)
• Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment [3.2371089062298317]
  Grad-CL is a novel source-free domain adaptation framework.<n>It adapts segmentation performance without requiring access to original source data.<n>It outperforms state-of-the-art unsupervised and source-free domain adaptation methods.
  arXiv  Detail & Related papers  (2025-09-12T10:51:46Z)
• ERSR: An Ellipse-constrained pseudo-label refinement and symmetric regularization framework for semi-supervised fetal head segmentation in ultrasound images [11.602941736726633]
  We propose a novel semi-supervised framework, ERSR, for fetal head ultrasound segmentation.<n>Our framework consists of the dual-scoring adaptive filtering strategy, the ellipse-constrained pseudo-label refinement, and the symmetry-based multiple consistency regularization.<n>Our method achieves state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T12:01:57Z)
• ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation [12.088386261002762]
  Source-Free Domain Adaptation (SFDA) aims to train a target model without source data, and the key is to generate pseudo-labels.<n>We observe that the source model often produces highly uncertain pseudo-labels for hard samples, particularly those heavily affected by domain shifts.<n>We propose a novel Progressive Curriculum Labeling (ElimPCL) method, which iteratively filters trustworthy pseudo-labeled samples.<n>Extensive experiments validate the effectiveness of ElimPCL, achieving up to a 3.4% improvement on challenging tasks.
  arXiv  Detail & Related papers  (2025-03-31T04:28:27Z)
• HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization [15.13875300007579]
  HisynSeg is a weakly-supervised semantic segmentation framework based on image-mixing synthesis and consistency regularization.<n>HisynSeg achieves a state-of-the-art performance on three datasets.
  arXiv  Detail & Related papers  (2024-12-30T13:10:48Z)
• Extracting Clean and Balanced Subset for Noisy Long-tailed Classification [66.47809135771698]
  We develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching. By setting a manually-specific probability measure, we can reduce the side-effects of noisy and long-tailed data simultaneously. Our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
  arXiv  Detail & Related papers  (2024-04-10T07:34:37Z)
• Domain Adaptive Synapse Detection with Weak Point Annotations [63.97144211520869]
  We present AdaSyn, a framework for domain adaptive synapse detection with weak point annotations. In the WASPSYN challenge at I SBI 2023, our method ranks the 1st place.
  arXiv  Detail & Related papers  (2023-08-31T05:05:53Z)
• Cross-modal tumor segmentation using generative blending augmentation and self training [1.6440045168835438]
  We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique. Generative Blending Augmentation (GBA) learns representative generative features from a single training image to realistically diversify tumor appearances. The proposed solution ranked first for vestibular schwannoma (VS) segmentation during the validation and test phases of the MICCAI CrossMoDA 2022 challenge.
  arXiv  Detail & Related papers  (2023-04-04T11:01:46Z)
• MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection [76.97324120775475]
  Cross-domain keypoint detection methods always require accessing the source data during adaptation. This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
  arXiv  Detail & Related papers  (2023-02-09T12:06:08Z)
• SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation [58.61946589036262]
  This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. We propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT.
  arXiv  Detail & Related papers  (2022-03-29T02:48:08Z)
• Improved Slice-wise Tumour Detection in Brain MRIs by Computing Dissimilarities between Latent Representations [68.8204255655161]
  Anomaly detection for Magnetic Resonance Images (MRIs) can be solved with unsupervised methods. We have proposed a slice-wise semi-supervised method for tumour detection based on the computation of a dissimilarity function in the latent space of a Variational AutoEncoder. We show that by training the models on higher resolution images and by improving the quality of the reconstructions, we obtain results which are comparable with different baselines.
  arXiv  Detail & Related papers  (2020-07-24T14:02:09Z)

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.