无需标注数据，让细胞分割模型自动适应新数据域。
SelfAdapt: Unsupervised Domain Adaptation of Cell Segmentation Models
- 用教师-学生一致性训练+无标签停止条件，实现无监督域适应。
- 在LiveCell和TissueNet上，AP0.5最高提升29.64%。
- 可无缝集成到Cellpose，适合缺乏标注的生物图像分析场景。
深度神经网络已成为生物医学实例分割的主流方法。通用模型如Cellpose在多种细胞数据上表现优异，但在与训练数据差异较大的领域中性能下降。尽管有监督微调可缓解此问题，但需标注数据，而这类数据往往难以获取。本文提出SelfAdapt，一种无需标签即可适配预训练细胞分割模型的方法。该方法基于学生-教师增强一致性训练，引入L2-SP正则化和无标签停止准则。我们在LiveCell和TissueNet数据集上评估，结果表明相比基线Cellpose，AP0.5相对提升最高达29.64%。此外，我们还证明，该无监督适应可进一步提升已有监督微调后的模型性能。SelfAdapt已作为Cellpose框架的即插即用扩展发布，代码公开于https://github.com/Kainmueller-Lab/self_adapt。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。