AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation

Qi Wen, Jiezhou He, Zhiming Luo, Shaozi Li

NeurIPS 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation

Read the paperCheck your idea against 137,217 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 BAPM, a training-free few-shot medical image segmentation method that mines boundary-aware prompts (positive and background cues) for SAM from support images.

Problem

Few-shot medical image segmentation with SAM via prompt engineering typically locates positive prompts from support images while ignoring informative background cues, making segmentation prone to errors near boundaries.

Approach

Mines boundary-aware prompts that combine positive foreground cues with background cues from support images to guide SAM without any training, rather than relying only on positive prompts.

Experimental setup

Builds on: Segment Anything Model

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy