{"ID":2835389,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22948","arxiv_id":"2511.22948","title":"Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation","abstract":"Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promise, they introduce inherent misalignment between generated images and semantic masks. This paper presents FLEX-Seg (FLexible Edge eXploitation for Segmentation), a framework that transforms this limitation into an opportunity for robust learning. FLEX-Seg comprises three key components: (1) Granular Adaptive Prototypes that captures boundary characteristics across multiple scales, (2) Uncertainty Boundary Emphasis that dynamically adjusts learning emphasis based on prediction entropy, and (3) Hardness-Aware Sampling that progressively focuses on challenging examples. By leveraging inherent misalignment rather than enforcing strict alignment, FLEX-Seg learns robust representations while capturing rich stylistic variations. Experiments across five real-world datasets demonstrate consistent improvements over state-of-the-art methods, achieving 2.44% and 2.63% mIoU gains on ACDC and Dark Zurich. Our findings validate that adaptive strategies for handling imperfect synthetic data lead to superior domain generalization. Code is available at https://github.com/VisualScienceLab-KHU/FLEX-Seg.","short_abstract":"Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promise, they introduce inherent misalignment between generated images and semantic masks. This paper presents FLEX-Seg (FLexible Edge eXploitatio...","url_abs":"https://arxiv.org/abs/2511.22948","url_pdf":"https://arxiv.org/pdf/2511.22948v1","authors":"[\"Taeyeong Kim\",\"SeungJoon Lee\",\"Jung Uk Kim\",\"MyeongAh Cho\"]","published":"2025-11-28T07:46:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":606508,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2835389,"paper_url":"https://arxiv.org/abs/2511.22948","paper_title":"Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation","repo_url":"https://github.com/VisualScienceLab-KHU/FLEX-Seg","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}