Sign in

EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection

By Yunni Qu and others
Expansive Matching of Experts (EMOE) is a novel method that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty based rejection on out-of-distribution (OOD) points. We propose an expansive data augmentation technique that generates OOD instances in a latent space, and an empirical trial based approach to filter out augmented... Show more
June 5, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection
Click on play to start listening