Adaptive Texture Filtering for Single-Domain Generalized Segmentation

Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features. Existing methods diversify images source domain by adding complex or even abnormal textures reduce sensitivity domain-specific However, these approaches depends heavily richness of texture bank and training them can be time-consuming. In contrast importing arbitrarily augmenting styles randomly, we focus single itself achieve generalization. this paper, present a novel adaptive filtering mechanism suppress influence without using augmentation, thus eliminating interference Further, design hierarchical guidance network equipped with structure-guided enhancement modules, which purpose learn generalized knowledge. Extensive experiments together ablation studies widely-used datasets are conducted verify effectiveness proposed model, reveal its superiority over other state-of-the-art alternatives.