cs.CVNov 16, 2026

SCoRe: Support-Calibrated Role Fusion for Training-Free Cross-Domain Few-Shot Segmentation

Authors: Abhishek Kathpal, Adarsh Jagan Sathyamoorthy, Utsav Patel

Organizations: Inception Robotics, LLC College Park, MD, USA

Abstract

We present SCoRe (Support-Calibrated Role fusion), a framework to utilize two complementary vision foundation model-based (VFM) segmenters for training-free cross-domain few-shot segmentation (CD-FSS). Our approach is based on the observation that current VFMs for CD-FSS possess capabilities where one model locates the correct object, while another model computes the better contour. Our approach uses: 1. a method to identify a VFM segmenter to lead Few-Shot Segmentation (FSS) task for a given concept, 2. a novel deterministic boundary correction method using bands of near- and far-pixels at the lead segmenter's predicted boundary of an object, and 3. a region correction mechanism for the other segmenter to conservatively prune components, fill holes, and bridge short gaps on the lead segmenter's predicted masks to improve accuracy. We evaluate SCoRe using RSRM and FSS-SAM3 across 3,314 matched five-shot episodes from 10 datasets. SCoRe achieves 72.738% foreground mIoU averaged across datasets, a gain of 5.210 percentage points over RSRM (paired 95% CI [4.618, 5.972]), with per-dataset gains up to 8.461 points over the strongest standalone method and the best point estimate on 7 of 10 datasets.

Figures & tables

Explore similar work

CardsList
  1. Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching

    Jun 23, 2026Sujun Sun, Mingwu Ren, Haofeng ZhangFew-Shot LearningCross-Domain Transfer Learning

  2. Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation

    Jun 23, 2026Sujun Sun, Mingwu Ren, Haofeng ZhangPrototype-Based LearningCross-Domain Generalization