RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation

TL;DR

RPG-SAM introduces a training-free one-shot polyp segmentation framework that addresses regional and response heterogeneity through reliability-weighted prototypes and adaptive thresholding, improving segmentation accuracy.

Contribution

The paper presents novel methods for handling heterogeneity in support and query images, including reliability-weighted prototype mining and geometric adaptive selection, with an iterative refinement process.

Findings

Achieves 5.56% mIoU improvement on Kvasir dataset.

Addresses regional heterogeneity with reliability-weighted prototypes.

Handles response heterogeneity with adaptive thresholding.

Abstract

Training-free one-shot segmentation offers a scalable alternative to expert annotations where knowledge is often transferred from support images and foundation models. But existing methods often treat all pixels in support images and query response intensities models in a homogeneous way. They ignore the regional heterogeity in support images and response heterogeity in query.To resolve this, we propose RPG-SAM, a framework that systematically tackles these heterogeneity gaps. Specifically, to address regional heterogeneity, we introduce Reliability-Weighted Prototype Mining (RWPM) to prioritize high-fidelity support features while utilizing background anchors as contrastive references for noise suppression. To address response heterogeneity, we develop Geometric Adaptive Selection (GAS) to dynamically recalibrate binarization thresholds by evaluating the morphological consensus of candidates. Finally, an iterative refinement loop method is designed to polishes anatomical boundaries. By accounting for multi-layered information heterogeneity, RPG-SAM achieves a 5.56\% mIoU improvement on the Kvasir dataset. Code will be released.