CVLGAug 15, 2025

SelfAdapt: Unsupervised Domain Adaptation of Cell Segmentation Models

arXiv:2508.11411v11 citationsh-index: 2Has Code2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Originality Incremental advance
AI Analysis

This work addresses the challenge of adapting biomedical segmentation models to new domains without costly annotations, which is incremental as it builds on existing consistency training methods.

The paper tackles the problem of domain adaptation for cell segmentation models without requiring labeled data, achieving up to 29.64% relative improvement in AP0.5 over baseline methods on datasets like LiveCell and TissueNet.

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 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes