Skip to content

Codebase for "LaSCal: Label-Shift Calibration without target labels", published at NeurIPS 2024.

Notifications You must be signed in to change notification settings

tpopordanoska/label-shift-calibration

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LaSCal: Label-Shift Calibration without target labels

This is the official code repository for "LaSCal: Label-Shift Calibration without target labels", published at NeurIPS 2024.

In this work, we propose LaSCal, a label-free, consistent calibration error estimator for label shift, paired with a post-hoc calibration strategy for unsupervised calibration. Label shift assumes changes in the label distribution while keeping the conditional distribution fixed. Our method is validated through extensive empirical analysis, demonstrating its reliability across diverse modalities, model architectures, and shift intensities.

About

Codebase for "LaSCal: Label-Shift Calibration without target labels", published at NeurIPS 2024.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages