Research
Is SAM3 ready for pathology segmentation?
arXiv:2604.18225v1 Announce Type: new Abstract: Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales
arXiv:2604.18225v1 Announce Type: new Abstract: Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales, where traditional methods often suffer from high annotation costs and poor generalization. SAM3 introduces Promptable Concept Segmentation, offering a potential automated interface via text prompts. With this work, we propose a systematic evaluation protocol to explore the capability space of SAM3 in a structured manner. Specifically, we evaluate SAM3 under different supervision settings including zero-shot, few-shot, and supervised with varying prompting strategies. Our extensive evaluation on pathological datasets including NuInsSeg, PanNuke and GlaS, reveals that: 1.text-only prompts poorly activate nuclear concepts. 2.performance is highly sensitive to visual prompt types and budgets. 3.few-shot learning offers gains, but SAM3 lacks robustness against visual prompt noise. and 4.a significant gap persists between prompt-based usage and task-trained adapter-based reference. Our study delineates SAM3's boundaries in pathology image segmentation and provides practical guidance on the necessity of pathology domain adaptation.
Related
- S4M: 4-points to Segment Anything
- A 3D SAM-Based Progressive Prompting Framework for Multi-Task Segmentation of Radiotherapy-induced Normal Tissue Injuries in Limited-Data Settings
- Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation
- H-SPAM: Hierarchical Superpixel Anything Model
- PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion
Source: arXiv cs.CV | 2026-04-21