RankMixup: Ranking-Based Mixup Training for Network Calibration

Network calibration aims to accurately estimate the level of confidences, which is particularly important for employing deep neural networks in real-world systems.

Data and Resources

Cite this as

Jongyoun Noh, Hyekang Park, Junghyup Lee, Bumsub Ham (2024). Dataset: RankMixup: Ranking-Based Mixup Training for Network Calibration. https://doi.org/10.57702/9vdmewx3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2308.11990
Author Jongyoun Noh
More Authors
Hyekang Park
Junghyup Lee
Bumsub Ham
Homepage https://cvlab.yonsei.ac.kr/projects/RankMixup