Score: 2

Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation

Published: November 28, 2025 | arXiv ID: 2511.22948v1

By: Taeyeong Kim , SeungJoon Lee , Jung Uk Kim and more

Potential Business Impact:

Teaches computers to understand pictures better, even when messy.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
🇰🇷 Korea, Republic of

Repos / Data Links

Page Count
18 pages

Category
Computer Science:
CV and Pattern Recognition