# CellStyle: Improved Zero-Shot Cell Segmentation via Style Transfer

Source: [CellStyle: Improved Zero-Shot Cell Segmentation via Style Transfer](<https://www.sota2.com/research/paper/68fa77631e209131cea72f57>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-28T05:00:19.604Z

Authors: R\\"uveyda Yilmaz, Zhu Chen, Yuli Wu, Johannes Stegmaier

Published: 2025-03-11T16:39:09.000Z

## Abstract

Cell microscopy data are abundant; however, corresponding segmentation annotations remain scarce. Moreover, variations in cell types, imaging devices, and staining techniques introduce significant domain gaps between datasets. As a result, even large, pretrained segmentation models trained on diverse datasets (source datasets) struggle to generalize to unseen datasets (target datasets). To overcome this generalization problem, we propose CellStyle, which improves the segmentation quality of such models without requiring labels for the target dataset, thereby enabling zero-shot adaptation. CellStyle transfers the attributes of an unannotated target dataset, such as texture, color, and noise, to the annotated source dataset. This transfer is performed while preserving the cell shapes of the source images, ensuring that the existing source annotations can still be used while maintaining the visual characteristics of the target dataset. The styled synthetic images with the existing annotations enable the finetuning of a generalist segmentation model for application to the unannotated target data. We demonstrate that CellStyle significantly improves zero-shot cell segmentation performance across diverse datasets by finetuning multiple segmentation models on the style-transferred data. The code will be made publicly available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Cell Segmentation on Fluo-HeLa CTC (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-fluo-hela-ctc-test.md>): Cell Segmentation; Fluo-HeLa CTC (test); SEG: 88.

- [Cell Segmentation on Fluo-GOWT1 CTC (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-fluo-gowt1-ctc-test.md>): Cell Segmentation; Fluo-GOWT1 CTC (test); SEG: 92.

- [Cell Segmentation on Pair 1 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-1-test.md>): Cell Segmentation; Pair 1 (test); SEG: 62.

- [Cell Segmentation on Pair 2 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-2-test.md>): Cell Segmentation; Pair 2 (test); Segmentation Score: 85.

- [Cell Segmentation on Pair 3 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-3-test.md>): Cell Segmentation; Pair 3 (test); SEG Score: 0.81.

- [Cell Segmentation on Pair 4 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-4-test.md>): Cell Segmentation; Pair 4 (test); Segmentation Score: 90.

- [Cell Segmentation on Pair 5 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-5-test.md>): Cell Segmentation; Pair 5 (test); SEG Score: 0.76.

- [Cell Segmentation on Pair 6 (test)](<https://www.sota2.com/research/sota/cell-segmentation-on-pair-6-test.md>): Cell Segmentation; Pair 6 (test); SEG: 58.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.08603>)

[PDF](<https://arxiv.org/pdf/2503.08603.pdf>)