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

2026-06-23

AI Summary

This work addresses the high computational cost and overfitting issues inherent in training-dependent approaches for cross-domain few-shot segmentation, as well as the limited or even degraded performance observed when integrating current vision foundation models. To overcome these challenges, the paper introduces the first fully training-free segmentation framework. Built upon the DINOv3 self-supervised encoder, the method leverages three key components—Semantic-Aware Feature Refusion (SAFR), Adaptive Support Enhancement (ASE), and Hybrid Prototype Matching (HPM)—to enable effective segmentation of unseen categories. Evaluated on four target-domain datasets, the proposed approach achieves state-of-the-art performance, substantially improving cross-domain generalization and demonstrating the efficacy and robustness of a training-free paradigm in few-shot segmentation.

Abstract

Cross-domain Few-shot Segmentation (CD-FSS) aims to transfer knowledge learned from source domain to distinct target domains, segmenting unseen target classes with only a few annotated samples. Although existing methods have made significant progress, they still rely on training or fine-tuning processes, which incur high computational costs and risk overfitting. We observe that when powerful and general-purpose vision foundation models are incorporated into these methods, their performance shows only marginal improvement or even degrades due to overfitting. To address this, we eliminate trainable parameters and propose a training-free framework to avoid both training overhead and overfitting. Built upon the self-supervised vision encoder DINOv3, our framework addresses cross-domain challenges through three core modules. First, the Semantic-aware Feature Re-fusion (SAFR) module identifies and re-fuses features that emphasize semantic patterns, generating representations with enhanced semantic discriminability. Additionally, the Adaptive Support Enhancement (ASE) module narrows semantic gaps between support and query through robust query information aggregation. Finally, the Hybrid Prototype Matching (HPM) module integrates matching results from diverse prototypes to adapt to varying semantic complexity across domains. Extensive experiments on four target domain datasets demonstrate that our method achieves state-of-the-art performance in CD-FSS without any training.

Problem

• Cross-domain Few-shot Segmentation
• training-free
• overfitting
• semantic representation
• vision foundation models

Innovation

• training-free
• cross-domain few-shot segmentation
• semantic-aware feature re-fusion
• adaptive support enhancement
• hybrid prototype matching