Research map / Architectures and efficiency / Mixture of experts
Gate to the Vessel: Residual Experts Restore What SAM Overlooks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes FineSAM++, a structure-aware sparse mixture-of-experts framework that refines SAM segmentation outputs on fine-grained medical structures such as vessels using confidence-driven soft gating.
Problem
Foundation segmentation models like SAM generalize well on natural images but produce localized failures on fine-grained medical structures such as vessels with complex morphology and indistinct boundaries.
Approach
A residual sparse expert module that is gated by a confidence-driven soft gate to correct SAM outputs where SAM is uncertain, with structure-aware experts targeting vessel morphology.
Experimental setup
Builds on: Segment Anything
Closest papers by meaning
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation (CVPR 2025 · similarity 0.87)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.87)
- VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging (CVPR 2025 · similarity 0.85)
- SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement (ICLR 2025 · similarity 0.85)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.84)
- Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.