LASA：面向域泛化语义分割的语言与源锚定对齐
LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation
浏览论文内容
中文总结 AI 辅助
针对域泛化语义分割中传统方法损害特征完整性的问题，提出LASA框架，含三个协同组件，实验显示其性能优于现有最优方法。
中文摘要 AI 辅助
域泛化语义分割（DGSS）聚焦于将带标注源域的知识泛化至训练阶段不可用数据的未见目标域。传统方法利用风格随机化或特征归一化缓解域偏移，但常损害特征完整性：风格随机化因粗粒度特性扭曲底层特征流形，特征归一化则因设计刚性抑制具判别性、域敏感的语义细节。为解决这些局限，我们提出语言与源锚定对齐（LASA）框架，包含三个协同组件：文本与源引导风格迁移（TSGST）、域感知查询适配器（DAQA）、域感知解码器优化器（DADO）。具体而言，TSGST模块以源特征为结构锚、视觉语言模型（VLM）先验为细粒度引导，解决流形扭曲问题；DAQA模块通过类别引导与域感知签名重新校准目标查询，恢复被抑制的具判别性与域敏感细节；DADO模块将所得查询分布与共享分类器对齐，确保跨域类别响应一致。在挑战性基准上的大量实验表明，我们的方法显著优于现有最优方法。
英文摘要
Domain Generalization Semantic Segmentation (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains where data is unavailable during the training phase. While conventional methods utilize style randomization or feature normalization to mitigate domain shifts, they often impair feature integrity. Specifically, style randomization distorts the underlying feature manifold due to its coarse-grained nature, while feature normalization suppresses discriminative, domain-sensitive semantic details owing to its rigid design. To address these limitations, we propose the Language-and-Source-Anchored Alignment (LASA) framework, which comprises three synergistic components: Text-and-Source-Guided Style Transfer (TSGST), Domain-Aware Query Adapter (DAQA), and Domain-Aware Decoder Optimizer (DADO). Concretely, the TSGST module addresses manifold distortion by utilizing source features as structural anchors and vision-language model (VLM) priors as fine-grained guidance. To restore suppressed discriminative and domain-sensitive details, the DAQA module recalibrates object queries via categorical guidance and domain-aware signatures, while the DADO module aligns the resulting query distributions with a shared classifier to ensure consistent categorical responses across domains. Extensive experiments on challenging benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches.
发表机构
- Xiamen University（厦门大学）
机构由 AI 辅助整理，请以论文原文为准。
