New CSG-Mamba model enhances endoscopic polyp segmentation accuracy

Researchers have developed CSG-Mamba, a new convolutional scoring gating Vision State Space network designed for improved endoscopic polyp segmentation. This model, built on a VM-UNet architecture, incorporates a Convolutional Scoring Gating module at its bottleneck to recalibrate state-space features. Experiments on the Kvasir-SEG and CVC-ColonDB datasets demonstrate that CSG-Mamba outperforms baseline models in overlap and recall metrics while maintaining competitive boundary accuracy. AI

IMPACT This model could improve the accuracy of computer-aided colonoscopy, potentially leading to earlier and more precise polyp detection.

RANK_REASON The cluster contains a research paper detailing a novel model for a specific computer vision task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• CSG-Mamba
• CVC-ColonDB
• Hugging Face
• Kvasir-SEG
• Mamba
• VM-UNet

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →