AI RESEARCH

Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation

arXiv CS.CV

ArXi:2604.02868v1 Announce Type: cross Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution shifts between generated and real images across scenarios, and such mismatches can markedly degrade downstream performance.