Seungjin Jung — accepted AI-conference papers

2025

Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing

Seungjin Jung, Kanghee Lee, Yonghyun Jeong, Haeun Noh, Jungmin Lee, Jongwon Choi

ICCV 2025poster

Domain Generalizable Face Anti-Spoofing (DG-FAS) methods effectively capture domain-invariant features by aligning the directions (weights) of local decision boundaries across domains. However, the bias terms associated with these boundaries remain misaligned, leading to inconsistent classification…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

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

Seungjin Jung, Seungmo Seo, Yonghyun Jeong, Jongwon Choi

ICML 2023poster

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. To resolve the issue, we propose a new calibration met…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗