# LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation

arXiv: https://arxiv.org/abs/2608.08805 · HTML: https://mlsanity.com/paper/2608.08805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Iterative Normalization: Beyond Standardization towards Efficient Whitening](https://mlsanity.com/paper/1904.03441/) (2019)
- [Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2204.02548/) (2022)
- [Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2207.04892/) (2022)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control](https://mlsanity.com/paper/2312.03048/) (2023)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [Collaborating Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.09788/) (2023)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [A Simple Recipe for Language-guided Domain Generalized Segmentation](https://mlsanity.com/paper/2311.17922/) (2023)
- [Texture Learning Domain Randomization for Domain Generalized Segmentation](https://mlsanity.com/paper/2303.11546/) (2023)
- [Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning](https://mlsanity.com/paper/2403.06122/) (2024)
- [Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning](https://mlsanity.com/paper/2303.01906/) (2023)

## Abstract (arXiv)

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.