DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909138377768960 |
|---|---|
| author | Zhao, Qilong Zhang, Yifei Zhu, Mengdan Gu, Siyi Gao, Yuyang Yang, Xiaofeng Zhao, Liang |
| author_facet | Zhao, Qilong Zhang, Yifei Zhu, Mengdan Gu, Siyi Gao, Yuyang Yang, Xiaofeng Zhao, Liang |
| contents | Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10831 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation Zhao, Qilong Zhang, Yifei Zhu, Mengdan Gu, Siyi Gao, Yuyang Yang, Xiaofeng Zhao, Liang Computer Vision and Pattern Recognition Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications. |
| title | DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.10831 |