SelfAdapt: Unsupervised Domain Adaptation of Cell Segmentation Models

Fabian Hubert Reith, Jannik Franzen, Josef Lorenz Rumberger, Dagmar Kainmueller; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 5812-5819

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. We propose SelfAdapt, 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 on the LiveCell and TissueNet datasets, demonstrating relative improvements in AP_ 0.5 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.