Abstract
Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due to privacy concerns and security constraints. Traditional fine-tuning or adaptation is hindered, leading to the demand for input-level strategies that can enhance generalization without modifying model weights. To this end, we propose a \textbf{S}tyle-\textbf{A}daptive \textbf{GE}neralization framework (\textbf{SAGE}), which improves the generalization of frozen models under privacy constraints. SAGE learns to synthesize visual prompts that implicitly align feature distributions across styles instead of directly fine-tuning the backbone. Specifically, we first utilize style transfer to construct a diverse style representation of the source domain, thereby learning a set of style characteristics that can cover a wide range of visual features. Then, the model adaptively fuses these style cues according to the visual context of each input, forming a dynamic prompt that harmonizes the image appearance without touching the interior of the model. Through this closed-loop design, SAGE effectively bridges the gap between frozen model invariance and the diversity of unseen domains. Extensive experiments on five benchmark datasets demonstrate that SAGE achieves competitive or superior performance compared to state-of-the-art methods under privacy constraints and outperforms full fine-tuning baselines in all settings.
Abstract (translated)
领域泛化在语义分割中的目标是缓解由于领域偏移导致的模型性能下降。然而，在许多现实场景中，由于隐私和安全限制的原因，我们无法访问模型参数和架构细节。这使得传统的微调或适应方法受到阻碍，从而产生了需求：通过不修改模型权重的方式来提高泛化能力的方法。为此，我们提出了一个名为**SAGE（Style-Adaptive Generalization框架）**的方案，该框架旨在改进在隐私限制下的冻结模型的泛化性能。 SAGE的学习方式是合成视觉提示，以隐式地跨风格对齐特征分布，而不是直接微调骨干网络。具体来说，我们首先利用风格迁移构建源领域的多样化的风格表示，从而学习一套覆盖广泛视觉特性的风格特征。然后，该模型根据每个输入的视觉上下文自适应融合这些风格线索，形成一个动态提示，这有助于协调图像外观而不触及模型内部结构。通过这种闭环设计，SAGE有效弥合了冻结模型不变性和未见领域多样性的差距。 在五个基准数据集上的广泛实验表明，在隐私限制下，SAGE与现有最佳方法相比取得了竞争性或优越的性能，并且在所有设置中均优于全量微调基线。
URL
https://arxiv.org/abs/2512.02369
