A Conformal Prediction Score that is Robust to Label Noise
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914803756302336 |
|---|---|
| author | Penso, Coby Goldberger, Jacob |
| author_facet | Penso, Coby Goldberger, Jacob |
| contents | Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the problem of CP calibration based on a validation set with noisy labels. We introduce a conformal score that is robust to label noise. The noise-free conformal score is estimated using the noisy labeled data and the noise level. In the test phase the noise-free score is used to form the prediction set. We applied the proposed algorithm to several standard medical imaging classification datasets. We show that our method outperforms current methods by a large margin, in terms of the average size of the prediction set, while maintaining the required coverage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Conformal Prediction Score that is Robust to Label Noise Penso, Coby Goldberger, Jacob Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the problem of CP calibration based on a validation set with noisy labels. We introduce a conformal score that is robust to label noise. The noise-free conformal score is estimated using the noisy labeled data and the noise level. In the test phase the noise-free score is used to form the prediction set. We applied the proposed algorithm to several standard medical imaging classification datasets. We show that our method outperforms current methods by a large margin, in terms of the average size of the prediction set, while maintaining the required coverage. |
| title | A Conformal Prediction Score that is Robust to Label Noise |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.02648 |