Search Results for author: Seungjin Jung

Found 1 papers, 1 papers with code

Scaling of Class-wise Training Losses for Post-hoc Calibration

1 code implementation19 Jun 2023 Seungjin Jung, Seungmo Seo, Yonghyun Jeong, Jongwon Choi

The class-wise training losses often diverge as a result of the various levels of intra-class and inter-class appearance variation, and we find that the diverging class-wise training losses cause the uncalibrated prediction with its reliability.

Cannot find the paper you are looking for? You can Submit a new open access paper.