DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
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_ | 1866913406082088960 |
|---|---|
| author | Fang, Yingying Wu, Shuang Jin, Zihao Xu, Caiwen Wang, Shiyi Walsh, Simon Yang, Guang |
| author_facet | Fang, Yingying Wu, Shuang Jin, Zihao Xu, Caiwen Wang, Shiyi Walsh, Simon Yang, Guang |
| contents | In the field of medical imaging, particularly in tasks related to early disease detection and prognosis, understanding the reasoning behind AI model predictions is imperative for assessing their reliability. Conventional explanation methods encounter challenges in identifying decisive features in medical image classifications, especially when discriminative features are subtle or not immediately evident. To address this limitation, we propose an agent model capable of generating counterfactual images that prompt different decisions when plugged into a black box model. By employing this agent model, we can uncover influential image patterns that impact the black model's final predictions. Through our methodology, we efficiently identify features that influence decisions of the deep black box. We validated our approach in the rigorous domain of medical prognosis tasks, showcasing its efficacy and potential to enhance the reliability of deep learning models in medical image classification compared to existing interpretation methods. The code will be publicly available at https://github.com/ayanglab/DiffExplainer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_15182 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation Fang, Yingying Wu, Shuang Jin, Zihao Xu, Caiwen Wang, Shiyi Walsh, Simon Yang, Guang Computer Vision and Pattern Recognition In the field of medical imaging, particularly in tasks related to early disease detection and prognosis, understanding the reasoning behind AI model predictions is imperative for assessing their reliability. Conventional explanation methods encounter challenges in identifying decisive features in medical image classifications, especially when discriminative features are subtle or not immediately evident. To address this limitation, we propose an agent model capable of generating counterfactual images that prompt different decisions when plugged into a black box model. By employing this agent model, we can uncover influential image patterns that impact the black model's final predictions. Through our methodology, we efficiently identify features that influence decisions of the deep black box. We validated our approach in the rigorous domain of medical prognosis tasks, showcasing its efficacy and potential to enhance the reliability of deep learning models in medical image classification compared to existing interpretation methods. The code will be publicly available at https://github.com/ayanglab/DiffExplainer. |
| title | DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.15182 |