Probabilistic Domain Adaptation for Biomedical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Archit, Anwai, Pape, Constantin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913970066030592
author Archit, Anwai
Pape, Constantin
author_facet Archit, Anwai
Pape, Constantin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11790
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Probabilistic Domain Adaptation for Biomedical Image Segmentation
Archit, Anwai
Pape, Constantin
Computer Vision and Pattern Recognition
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.
title Probabilistic Domain Adaptation for Biomedical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.11790