AI Paper Atlas

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

One Polyp Identifies All: One-Shot Polyp Segmentation with SAM via Cascaded Priors and Iterative Prompt Evolution

Xinyu Mao, Xiaohan Xing, Fei Meng, Jianbang Liu, Fan Bai, Qiang Nie, Max Meng

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scale-cascaded prior fusion (SPF) (ablation)OP-SAM (CPG only) · KvasirIoU: 67.12 -> 69.05Improved
add Euclidean prompt evolution (EPE) (ablation)OP-SAM (CPG+SPF) · KvasirIoU: 69.05 -> 76.93Improved
add self-correlation refinement to cross-correlation prior (ablation)OP-SAM CPG · Kvasir prior qualityIoU: 31.88 -> 58.30Improved
use SPF fusion instead of plain averaging with 3 support images (ablation)OP-SAM · Kvasir support typeIoU: 37.88 -> 57.23Improved
use SPF instead of averaging with lesion scaling augmentations (ablation)OP-SAM · Kvasir support typeIoU: 48.67 -> 61.47Improved
average scaled priors without SPF versus single image (ablation)OP-SAM · Kvasir support typeIoUHurt
increase support images from 3 to 5 with averaging (ablation)OP-SAM · Kvasir support typeIoU: 37.88 -> 44.53Improved
use EPE instead of top and bottom point prompts (ablation)OP-SAM · Kvasir prompting strategyIoU: 60.49 -> 76.93Improved
use Euclidean distance transform center instead of bounding box center (ablation)EPE · Kvasir prompting strategyIoU: 58.04 -> 76.93Improved
use tight/loose thresholds 0.7/0.5 instead of wide or narrow gaps (ablation)EPE · KvasirIoU: 76.93Improved
OP-SAM versus oracle three GT pointsOP-SAM · KvasirIoU: 71.88 -> 76.93Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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