This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914784683753472 |
|---|---|
| author | Vats, Anuja Mohammed, Ahmed Pedersen, Marius Wiratunga, Nirmalie |
| author_facet | Vats, Anuja Mohammed, Ahmed Pedersen, Marius Wiratunga, Nirmalie |
| contents | Due to the unequivocal need for understanding the decision processes of deep learning networks, both modal-dependent and model-agnostic techniques have become very popular. Although both of these ideas provide transparency for automated decision making, most methodologies focus on either using the modal-gradients (model-dependent) or ignoring the model internal states and reasoning with a model's behavior/outcome (model-agnostic) to instances. In this work, we propose a unified explanation approach that given an instance combines both model-dependent and agnostic explanations to produce an explanation set. The generated explanations are not only consistent in the neighborhood of a sample but can highlight causal relationships between image content and the outcome. We use Wireless Capsule Endoscopy (WCE) domain to illustrate the effectiveness of our explanations. The saliency maps generated by our approach are comparable or better on the softmax information score. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_02506 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy Vats, Anuja Mohammed, Ahmed Pedersen, Marius Wiratunga, Nirmalie Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Due to the unequivocal need for understanding the decision processes of deep learning networks, both modal-dependent and model-agnostic techniques have become very popular. Although both of these ideas provide transparency for automated decision making, most methodologies focus on either using the modal-gradients (model-dependent) or ignoring the model internal states and reasoning with a model's behavior/outcome (model-agnostic) to instances. In this work, we propose a unified explanation approach that given an instance combines both model-dependent and agnostic explanations to produce an explanation set. The generated explanations are not only consistent in the neighborhood of a sample but can highlight causal relationships between image content and the outcome. We use Wireless Capsule Endoscopy (WCE) domain to illustrate the effectiveness of our explanations. The saliency maps generated by our approach are comparable or better on the softmax information score. |
| title | This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.02506 |