用四色定理解决细胞实例分割中的邻接混淆问题。
The Four Color Theorem for Cell Instance Segmentation
- 将细胞视为国家，用四色编码区分相邻实例。
- 在多个数据集上达到顶尖性能，计算效率显著提升。
- 适合需要高精度细胞分割的生物医学图像分析场景。
细胞实例分割对生物医学图像分析至关重要，但准确区分紧密接触的细胞仍是一大挑战。现有基于检测、轮廓和距离映射的方法虽有进展，但在模型性能与计算效率间难以平衡。本文受四色定理启发，将细胞类比为国家，组织类比为海洋，提出一种四色编码方案，确保相邻实例获得不同标签。该方法将实例分割重构为仅需四类的约束语义分割问题，大幅简化实例区分过程。为解决四色编码非唯一性带来的训练不稳定性，设计渐进式训练策略与编码转换方法。大量实验表明，本方法在多种模式下均达当前最优性能。代码已开源：https://github.com/zhangye-zoe/FCIS。
原文摘要 · Abstract (English)
Cell instance segmentation is critical to analyzing biomedical images, yet accurately distinguishing tightly touching cells remains a persistent challenge. Existing instance segmentation frameworks, including detection-based, contour-based, and distance mapping-based approaches, have made significant progress, but balancing model performance with computational efficiency remains an open problem. In this paper, we propose a novel cell instance segmentation method inspired by the four-color theorem. By conceptualizing cells as countries and tissues as oceans, we introduce a four-color encoding scheme that ensures adjacent instances receive distinct labels. This reformulation transforms instance segmentation into a constrained semantic segmentation problem with only four predicted classes, substantially simplifying the instance differentiation process. To solve the training instability caused by the non-uniqueness of four-color encoding, we design an asymptotic training strategy and encoding transformation method. Extensive experiments on various modes demonstrate our approach achieves state-of-the-art performance. The code is available at https://github.com/zhangye-zoe/FCIS.
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。