Cell Instance Segmentation via Multi-Task Image-to-Image Schrodinger Bridge

arXiv:2604.12318v1 Announce Type: new Abstract: Existing cell instance segmentation pipelines typically combine deterministic predictions with post-processing, which imposes limited explicit constraints on the global structure of instance masks. In this work, we propose a multi-task image-to-image Schrodinger Bridge framework that formulates instance segmentation as a distribution-based image-to-image generation problem. Boundary-aware supervision is integrated through a reverse distance map, and deterministic inference is employed to produce stable predictions. Experimental results on the PanNuke dataset demonstrate that the proposed method achieves competitive or superior performance without relying on SAM pre-training or additional post-processing. Additional results on the MoNuSeg dataset show robustness under limited training data. These findings indicate that Schrodinger Bridge-based image-to-image generation provides an effective framework for cell instance segmentation.

Related

• M^{2}SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
• TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
• DeferredSeg: A Multi-Expert Deferral Framework for Trustworthy Medical Image Segmentation
• Scaling In-Context Segmentation with Hierarchical Supervision
• Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation
• FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation

Source: arXiv cs.CV | 2026-04-15