# Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentation Source: [Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:20:02.433Z Authors: Guanlong Jiao, Chenyangguang Zhang, Haonan Yin, Yu Mo, Biqing Huang, Hui Pan, Yi Luo, Jingxian Liu Published: 2024-04-21T16:05:38.000Z ## Abstract Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn the capability of generalized semantic segmentation towards the unseen target domains. Previous works typically address this challenge by global style randomization or feature regularization. In this paper, we argue that given the observation that different local semantic regions perform different visual characteristics from the source domain to the target domain, methods focusing on global operations are hard to capture such regional discrepancies, thus failing to construct domain-invariant representations with the consistency from local to global level. Therefore, we propose the Semantic-Rearrangement-based Multi-Level Alignment (SRMA) to overcome this problem. SRMA first incorporates a Semantic Rearrangement Module (SRM), which conducts semantic region randomization to enhance the diversity of the source domain sufficiently. A Multi-Level Alignment module (MLA) is subsequently proposed with the help of such diversity to establish the global-regional-local consistent domain-invariant representations. By aligning features across randomized samples with domain-neutral knowledge at multiple levels, SRMA provides a more robust way to handle the source-target domain gap. Extensive experiments demonstrate the superiority of SRMA over the current state-of-the-art works on various benchmarks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()