# Revisiting foundation models for cell instance segmentation

arXiv: https://arxiv.org/abs/2603.17845 · HTML: https://mlsanity.com/paper/2603.17845/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 70 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [PanNuke Dataset Extension, Insights and Baselines](https://mlsanity.com/paper/2003.10778/) (2020)
- [CellViT: Vision Transformers for Precise Cell Segmentation and Classification](https://mlsanity.com/paper/2306.15350/) (2023)
- [VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging](https://mlsanity.com/paper/2406.05285/) (2024)
- [CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological Images](https://mlsanity.com/paper/2101.00442/) (2021)
- [NuInsSeg: A Fully Annotated Dataset for Nuclei Instance Segmentation in H&E-Stained Histological Images](https://mlsanity.com/paper/2308.01760/) (2023)
- [UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images](https://mlsanity.com/paper/2402.16663/) (2024)
- [Segment Anything for Histopathology](https://mlsanity.com/paper/2502.00408/) (2025)
- [Tracking one-in-a-million: Large-scale benchmark for microbial single-cell tracking with experiment-aware robustness metrics](https://mlsanity.com/paper/2411.00552/) (2024)
- [CellSeg1: Robust Cell Segmentation with One Training Image](https://mlsanity.com/paper/2412.01410/) (2024)
- [MedicoSAM: Robust Improvement of SAM for Medical Imaging](https://mlsanity.com/paper/2501.11734/) (2025)

## Built on by (most cited first, 2 of 2)

- [Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy](https://mlsanity.com/paper/2603.19802/) (2026)
- [Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation](https://mlsanity.com/paper/2609.14080/) (2026)

## Abstract (arXiv)

Cell segmentation is a fundamental task in microscopy image analysis. Several foundation models for cell segmentation have been introduced, virtually all of them are extensions of Segment Anything Model (SAM), improving it for microscopy data. Recently, SAM2 and SAM3 have been published, further improving and extending the capabilities of general-purpose segmentation foundation models. Here, we comprehensively evaluate foundation models for cell segmentation (CellPoseSAM, CellSAM, μSAM) and for general-purpose segmentation (SAM, SAM2, SAM3) on a diverse set of (light) microscopy datasets, for tasks including cell, nucleus and organoid segmentation. Furthermore, we introduce a new instance segmentation strategy called automatic prompt generation (APG) that can be used to further improve SAM-based microscopy foundation models. APG consistently improves segmentation results for μSAM, which is used as the base model, and is competitive with the state-of-the-art model CellPoseSAM. Moreover, our work provides important lessons for adaptation strategies of SAM-style models to microscopy and provides a strategy for creating even more powerful microscopy foundation models. Our code is publicly available at https://github.com/computational-cell-analytics/micro-sam.