Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection

no code implementations • 23 Apr 2022 • Meng Xing, Zhiyong Feng, Yong Su, Changjae Oh

For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Parametric T-Spline Face Morphable Model for Detailed Fitting in Shape Subspace

no code implementations • CVPR 2017 • Weilong Peng, Zhiyong Feng, Chao Xu, Yong Su

As any pre-learnt subspace is not complete to handle the variety and details of faces and expressions, it covers a limited span of morphing.