SelfAdapt: unsupervised domain adaptation of cell segmentation models

Tools

Item Type:	Preprint
Title:	SelfAdapt: unsupervised domain adaptation of cell segmentation models
Creators Name:	Reith, Fabian H., Franzen, Jannik, Palli, Dinesh R., Rumberger, J. Lorenz and Kainmueller, Dagmar
Abstract:	Deep neural networks have become the go-to method for biomedical instance segmentation. Generalist models like Cellpose demonstrate state-of-the-art performance across diverse cellular data, though their effectiveness often degrades on domains that differ from their training data. While supervised fine-tuning can address this limitation, it requires annotated data that may not be readily available. WeproposeSelfAdapt, a method that enables the adaptation of pre-trained cell segmentation models without the need for labels. Our approach builds upon student-teacher augmentation consistency training, introducing L2-SP regularization and label-free stopping criteria. We evaluate our method ontheLiveCell and TissueNet datasets, demonstrating relative improvements in AP0.5 of up to 29.64% over baseline Cellpose. Additionally, we show that our unsupervised adaptation can further improve models that were previously fine-tuned with supervision. We release SelfAdapt as an easy-to-use extension of the Cellpose framework. The code for our method is publicly available at https: //github.com/Kainmueller-Lab/self_adapt.
Source:	arXiv
Publisher:	Cornell University
Article Number:	2508.11411
Date:	15 August 2025
Official Publication:	https://arxiv.org/abs/2508.11411

Repository Staff Only: item control page