Probabilistic Domain Adaptation for Biomedical Image Segmentation

Anwai Archit, Constantin Pape
3/21/2023
cs.CV

Official code: computational-cell-analytics/Probabilistic-Domain-Adaptation (6 stars, MIT, last commit 2025-07-04).

Abstract

Segmentation is a crucial analysis task in biomedical imaging. Given the diverse experimental settings in this field, the lack of generalization limits the use of deep learning in practice. Domain adaptation is a promising remedy: it involves training a model for a given task on a source dataset with labels and adapts it to a target dataset without additional labels. We introduce a probabilistic domain adaptation method, building on self-training approaches and the Probabilistic UNet. We use the latter to sample multiple segmentation hypotheses to implement better pseudo-label filtering. We further study joint and separate source-target training strategies and evaluate our method on three challenging domain adaptation tasks for biomedical segmentation. Our code is publicly available at https://github.com/computational-cell-analytics/Probabilistic-Domain-Adaptation.

View on arXivView PDF

Code Implementations(1)

computational-cell-analytics/Probabilistic-Domain-AdaptationOfficial100%
MIT

Probabilistic Domain Adaptation for Biomedical Image Segmentation

60PythonMar 17, 20231 years agoMIT
deep-learningdomain-adaptationelectron-microscopylivecelllung-xray+3 more

Similar Papers

Medical Image Segmentation with Domain Adaptation: A Survey

89% match2 repos2762023

Robust Source-Free Domain Adaptation for Fundus Image Segmentation

87% match1 repo132023

SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation

87% match2025

Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation

87% match1 repo992026

ConvLoRA and AdaBN based Domain Adaptation via Self-Training

86% match1 repo972024

Data Augmentation-Based Unsupervised Domain Adaptation In Medical Imaging

86% match2023

Cite this paper

@article{archit2023probabilistic,
  title  = {Probabilistic Domain Adaptation for Biomedical Image Segmentation},
  author = {Anwai Archit and Constantin Pape},
  year   = {2023},
  eprint = {2303.11790},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.11790v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.11790.svg)](https://codeofpaper.com/paper/2303.11790)

Discussion