AnoFPDM: Anomaly Segmentation with Forward Process of Diffusion Models for Brain MRI
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917886900043776 |
|---|---|
| author | Che, Yiming Rafsani, Fazle Shah, Jay Siddiquee, Md Mahfuzur Rahman Wu, Teresa |
| author_facet | Che, Yiming Rafsani, Fazle Shah, Jay Siddiquee, Md Mahfuzur Rahman Wu, Teresa |
| contents | Weakly-supervised diffusion models (DMs) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need for pixel-level labels in training, offering a more cost-effective alternative to supervised methods. However, existing methods are not fully weakly-supervised because they heavily rely on costly pixel-level labels for hyperparameter tuning in inference. To tackle this challenge, we introduce Anomaly Segmentation with Forward Process of Diffusion Models (AnoFPDM), a fully weakly-supervised framework that operates without the need of pixel-level labels. Leveraging the unguided forward process as a reference for the guided forward process, we select hyperparameters such as the noise scale, the threshold for segmentation and the guidance strength. We aggregate anomaly maps from guided forward process, enhancing the signal strength of anomalous regions. Remarkably, our proposed method outperforms recent state-of-the-art weakly-supervised approaches, even without utilizing pixel-level labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15683 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnoFPDM: Anomaly Segmentation with Forward Process of Diffusion Models for Brain MRI Che, Yiming Rafsani, Fazle Shah, Jay Siddiquee, Md Mahfuzur Rahman Wu, Teresa Computer Vision and Pattern Recognition Weakly-supervised diffusion models (DMs) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need for pixel-level labels in training, offering a more cost-effective alternative to supervised methods. However, existing methods are not fully weakly-supervised because they heavily rely on costly pixel-level labels for hyperparameter tuning in inference. To tackle this challenge, we introduce Anomaly Segmentation with Forward Process of Diffusion Models (AnoFPDM), a fully weakly-supervised framework that operates without the need of pixel-level labels. Leveraging the unguided forward process as a reference for the guided forward process, we select hyperparameters such as the noise scale, the threshold for segmentation and the guidance strength. We aggregate anomaly maps from guided forward process, enhancing the signal strength of anomalous regions. Remarkably, our proposed method outperforms recent state-of-the-art weakly-supervised approaches, even without utilizing pixel-level labels. |
| title | AnoFPDM: Anomaly Segmentation with Forward Process of Diffusion Models for Brain MRI |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.15683 |