mlsanityData to 7 Oct 2026

STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains

arXiv 2104.11596 ↗First posted 23 Apr 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose an unsupervised domain adaptation (UDA) approach for white matter hyperintensity (WMH) segmentation, which uses Self-Training with Uncertainty DEpendent Label refinement (STRUDEL). Self-training has recently been introduced as a highly effective method for UDA, which is based on self-generated pseudo labels. However, pseudo labels can be very noisy and therefore deteriorate model performance. We propose to predict the uncertainty of pseudo labels and integrate it in the training process with an uncertainty-guided loss function to highlight labels with high certainty. STRUDEL is further improved by incorporating the segmentation output of an existing method in the pseudo label generation that showed high robustness for WMH segmentation. In our experiments, we evaluate STRUDEL with a standard U-Net and a modified network with a higher receptive field. Our results on WMH segmentation across datasets demonstrate the significant improvement of STRUDEL with respect to standard self-training.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 23 Apr 2021.

Builds on

18 of 31 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  5. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  6. 2019Confidence Regularized Self-Trainingcited by 418
  7. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 378
  8. 2020Rethinking Pre-training and Self-trainingcited by 352
  9. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 258
  10. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  11. 2019Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolutioncited by 140
  12. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
6 more
  1. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  2. 2017Who Said What: Modeling Individual Labelers Improves Classificationcited by 77
  3. 2018Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blockscited by 75
  4. 2020Two-phase Pseudo Label Densification for Self-training based Domain Adaptationcited by 60
  5. 20183D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Trainingcited by 57
  6. 2017Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground Truthcited by 30

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 1.

4 papers.

  1. 2023Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectivescited by 24
  2. 2023SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentationcited by 10
  3. 2023Data efficient deep learning for medical image analysis: A surveycited by 6
  4. 2025Using Foundation Models as Pseudo-Label Generators for Pre-Clinical 4D Cardiac CT Segmentationcited by 1