2 citations · 3 across the 3 of their papers we have counts for
4 papers
Rethinking Detection Calibration: A Coordinate and Direction Perspective
Juyong Lee, Seungjin Jung, Jungmin Lee +2
Deep learning based object detectors require trustworthiness beyond competitive detection performance, but deep neural networks are prone to overconfident predictions, assigning hi…
Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion
Seungjin Jung, Yonghyun Jeong, Minha Kim +3
Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing their ability to handle unseen…
Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing
Seungjin Jung, Kanghee Lee, Yonghyun Jeong +3
Domain Generalizable Face Anti-Spoofing (DGFAS) methods effectively capture domain-invariant features by aligning the directions (weights) of local decision boundaries across domai…
Scaling of Class-wise Training Losses for Post-hoc Calibration
Seungjin Jung, Seungmo Seo, Yonghyun Jeong +1
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 traini…