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

arXiv: https://arxiv.org/abs/2608.17983 · HTML: https://mlsanity.com/paper/2608.17983/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer](https://mlsanity.com/paper/2112.04894/) (2021)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation](https://mlsanity.com/paper/2212.02078/) (2022)
- [UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2309.10244/) (2023)
- [UltraSuite: A Repository of Ultrasound and Acoustic Data from Child Speech Therapy Sessions](https://mlsanity.com/paper/1907.00835/) (2019)
- [Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning](https://mlsanity.com/paper/2307.09769/) (2023)
- [TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos](https://mlsanity.com/paper/2011.09804/) (2020)
- [Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation](https://mlsanity.com/paper/2304.00792/) (2023)
- [Medical Image Segmentation with Domain Adaptation: A Survey](https://mlsanity.com/paper/2311.01702/) (2023)
- [A CNN-based tool for automatic tongue contour tracking in ultrasound images](https://mlsanity.com/paper/1907.10210/) (2019)
- [AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2501.03074/) (2025)
- [Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism](https://mlsanity.com/paper/2106.11769/) (2021)
- [UltraUNet: Real-Time Ultrasound Tongue Segmentation for Diverse Linguistic and Imaging Conditions](https://mlsanity.com/paper/2509.23225/) (2025)
- [Transfer Learning for Ultrasound Tongue Contour Extraction with Different Domains](https://mlsanity.com/paper/1906.04301/) (2019)

## Abstract (arXiv)

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.