Saved in:
Bibliographic Details
Main Authors: McKenna, Stephen, Carse, Jacob
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.11456
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917696112689152
author McKenna, Stephen
Carse, Jacob
author_facet McKenna, Stephen
Carse, Jacob
contents We consider calibration of convolutional classifiers for diagnostic decision making. Clinical decision makers can use calibrated classifiers to minimise expected costs given their own cost function. Such functions are usually unknown at training time. If minimising expected costs is the primary aim, algorithms should focus on tuning calibration in regions of probability simplex likely to effect decisions. We give an example, modifying temperature scaling calibration, and demonstrate improved calibration where it matters using convnets trained to classify dermoscopy images.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11456
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Calibrating Where It Matters: Constrained Temperature Scaling
McKenna, Stephen
Carse, Jacob
Machine Learning
Computer Vision and Pattern Recognition
We consider calibration of convolutional classifiers for diagnostic decision making. Clinical decision makers can use calibrated classifiers to minimise expected costs given their own cost function. Such functions are usually unknown at training time. If minimising expected costs is the primary aim, algorithms should focus on tuning calibration in regions of probability simplex likely to effect decisions. We give an example, modifying temperature scaling calibration, and demonstrate improved calibration where it matters using convnets trained to classify dermoscopy images.
title Calibrating Where It Matters: Constrained Temperature Scaling
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.11456