Report
Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling
| العنوان: | Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling |
|---|---|
| المؤلفون: | Metta, Carlo, Guidotti, Riccardo, Yin, Yuan, Gallinari, Patrick, Rinzivillo, Salvatore |
| المصدر: | 2021 IEEE Symposium on Computers and Communications (ISCC) |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
| الوصف: | Explainable AI consists in developing mechanisms allowing for an interaction between decision systems and humans by making the decisions of the formers understandable. This is particularly important in sensitive contexts like in the medical domain. We propose a use case study, for skin lesion diagnosis, illustrating how it is possible to provide the practitioner with explanations on the decisions of a state of the art deep neural network classifier trained to characterize skin lesions from examples. Our framework consists of a trained classifier onto which an explanation module operates. The latter is able to offer the practitioner exemplars and counterexemplars for the classification diagnosis thus allowing the physician to interact with the automatic diagnosis system. The exemplars are generated via an adversarial autoencoder. We illustrate the behavior of the system on representative examples. Comment: arXiv admin note: text overlap with arXiv:2111.11863 |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1109/ISCC53001.2021.9631485 |
| URL الوصول: | http://arxiv.org/abs/2302.03033 |
| رقم الانضمام: | edsarx.2302.03033 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1109/ISCC53001.2021.9631485 |
|---|