Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentation

TL;DR

This paper introduces MGFC, a hierarchical feature calibration framework that leverages vision foundation models at multiple granularities to improve domain generalization in semantic segmentation tasks.

Contribution

It proposes a novel multi-granularity feature calibration method that aligns VFM features at coarse, medium, and fine levels for better domain robustness in semantic segmentation.

Findings

Outperforms state-of-the-art DGSS methods on benchmark datasets.

Effective hierarchical feature calibration improves segmentation accuracy.

Enhances robustness to domain shifts through multi-level feature adaptation.

Abstract

Domain Generalized Semantic Segmentation (DGSS) aims to improve the generalization ability of models across unseen domains without access to target data during training. Recent advances in DGSS have increasingly exploited vision foundation models (VFMs) via parameter-efficient fine-tuning strategies. However, most existing approaches concentrate on global feature fine-tuning, while overlooking hierarchical adaptation across feature levels, which is crucial for precise dense prediction. In this paper, we propose Multi-Granularity Feature Calibration (MGFC), a novel framework that performs coarse-to-fine alignment of VFM features to enhance robustness under domain shifts. Specifically, MGFC first calibrates coarse-grained features to capture global contextual semantics and scene-level structure. Then, it refines medium-grained features by promoting category-level feature discriminability. Finally, fine-grained features are calibrated through high-frequency spatial detail enhancement. By performing hierarchical and granularity-aware calibration, MGFC effectively transfers the generalization strengths of VFMs to the domain-specific task of DGSS. Extensive experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art DGSS approaches, highlighting the effectiveness of multi-granularity adaptation for the semantic segmentation task of domain generalization.