![[feed]](/style/images/feed-icon-14x14.png){kind=icon}
Tools
Tools
| Item Type: | Conference or Workshop Item |
|---|---|
| Title: | SelfAdapt: unsupervised domain adaptation of cell segmentation models |
| Creators Name: | Reith, Fabian H., Franzen, Jannik, 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. 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. The code for our method is publicly available at https://github.com/Kainmueller-Lab/self_adapt. |
| Keywords: | Source-Free Unsupervised Domain Adaptation, Early Stopping, Cell Instance Segmentation, Cellpose |
| Source: | 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) |
| Title of Book: | 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) |
| ISSN: | 2473-9936 |
| ISBN: | 979-8-3315-8989-9 |
| Publisher: | IEEE |
| Page Range: | 5871-5878 |
| Number of Pages: | 8 |
| Date: | 23 February 2026 |
| Official Publication: | https://doi.org/10.1109/iccvw69036.2025.00612 |
| Related to: |
Repository Staff Only: item control page
