Adaptive Texture Filtering for Single-Domain Generalized Segmentation
Xinhui Li, Mingjia Li, Yaxing Wang, Chuan-Xian Ren, Xiaojie Guo
Abstract
Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features. Existing methods diversify images in the source domain by adding complex or even abnormal textures to reduce the sensitivity to domain-specific features. However, these approaches depends heavily on the richness of the texture bank and training them can be time-consuming. In contrast to importing textures arbitrarily or augmenting styles randomly, we focus on the single source domain itself to achieve the generalization. In this paper, we present a novel adaptive texture filtering mechanism to suppress the influence of texture without using augmentation, thus eliminating the interference of domain-specific features. Further, we design a hierarchical guidance generalization network equipped with structure-guided enhancement modules, which purpose to learn the domain-invariant generalized knowledge. Extensive experiments together with ablation studies on widely-used datasets are conducted to verify the effectiveness of the proposed model, and reveal its superiority over other state-of-the-art alternatives.
BibTeX
@article{Li_Li_Wang_Ren_Guo_2023, title={Adaptive Texture Filtering for Single-Domain Generalized Segmentation}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25229}, DOI={10.1609/aaai.v37i2.25229}, abstractNote={Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features. Existing methods diversify images in the source domain by adding complex or even abnormal textures to reduce the sensitivity to domain-specific features. However, these approaches depends heavily on the richness of the texture bank and training them can be time-consuming. In contrast to importing textures arbitrarily or augmenting styles randomly, we focus on the single source domain itself to achieve the generalization. In this paper, we present a novel adaptive texture filtering mechanism to suppress the influence of texture without using augmentation, thus eliminating the interference of domain-specific features. Further, we design a hierarchical guidance generalization network equipped with structure-guided enhancement modules, which purpose to learn the domain-invariant generalized knowledge. Extensive experiments together with ablation studies on widely-used datasets are conducted to verify the effectiveness of the proposed model, and reveal its superiority over other state-of-the-art alternatives.}, number={2}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Li, Xinhui and Li, Mingjia and Wang, Yaxing and Ren, Chuan-Xian and Guo, Xiaojie}, year={2023}, month={Jun.}, pages={1442-1450} }