Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908934789398528 |
|---|---|
| author | Yang, Jie Ye, Ziqi Ke, Aihua Luo, Jian Cai, Bo Wang, Xiaosong |
| author_facet | Yang, Jie Ye, Ziqi Ke, Aihua Luo, Jian Cai, Bo Wang, Xiaosong |
| contents | 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. To address this issue, we propose AlignFlow, a flow matching model that aligns with the target reference image distribution via differentiable reward fine-tuning, and remains effective even when only a small number of reference images are provided. Specifically, we divide the training of the flow matching model into two stages: in the first stage, the model fits the training data to generate plausible images; Then, we introduce a distribution alignment mechanism and employ differentiable reward to steer the generated images toward the distribution of the given samples from the target domain. In addition, to enhance the diversity of generated masks, we also design a flow matching based mask generation to complement the diversity in regions of interest. Extensive experiments demonstrate the effectiveness of our approach, i.e., performance improvement by 3.5-4.0% in mDice and 3.5-5.6% in mIoU across a variety of datasets and scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02868 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation Yang, Jie Ye, Ziqi Ke, Aihua Luo, Jian Cai, Bo Wang, Xiaosong Image and Video Processing Computer Vision and Pattern Recognition 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. To address this issue, we propose AlignFlow, a flow matching model that aligns with the target reference image distribution via differentiable reward fine-tuning, and remains effective even when only a small number of reference images are provided. Specifically, we divide the training of the flow matching model into two stages: in the first stage, the model fits the training data to generate plausible images; Then, we introduce a distribution alignment mechanism and employ differentiable reward to steer the generated images toward the distribution of the given samples from the target domain. In addition, to enhance the diversity of generated masks, we also design a flow matching based mask generation to complement the diversity in regions of interest. Extensive experiments demonstrate the effectiveness of our approach, i.e., performance improvement by 3.5-4.0% in mDice and 3.5-5.6% in mIoU across a variety of datasets and scenarios. |
| title | Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02868 |