Vision Foundation Models (VFMs) excel in generalization due to large-scale pretraining, but fine-tuning them for Domain Generalized Semantic Segmentation (DGSS) while maintaining this ability remains challenging. Existing approaches either selectively fine-tune parameters or freeze the VFMs and update only the adapters, both of which may underutilize the VFMs' full potential in DGSS tasks. We observe that domain-sensitive parameters in VFMs, arising from task and distribution differences, can hinder generalization. To address this, we propose \textbf{FisherTune}, a robust fine-tuning method guided by the Domain-Related Fisher Information Matrix (DR-FIM). DR-FIM measures parameter sensitivity across tasks and domains, enabling selective updates that preserve generalization and enhance DGSS adaptability. FisherTune incorporates variational inference to stabilize DR-FIM estimation, treating parameters as Gaussian-distributed variables and leveraging pre-trained priors. Extensive experiments show that FisherTune achieves superior cross-domain segmentation while maintaining generalization, outperforming selective-parameter and adapter-based methods.
@article{arxiv.2503.17940,
title = {FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation},
author = {Dong Zhao and Jinlong Li and Shuang Wang and Mengyao Wu and Qi Zang and Nicu Sebe and Zhun Zhong},
journal= {arXiv preprint arXiv:2503.17940},
year = {2025}
}