2 problems

0 votes0 replies0 views
The K-means/center stability conjecture for statistical depth-based uncertainty scores
K-means/center stability conjecture. This averaging effect makes the method much more stable and facilitates capturing the overall shape of the cluster by avoiding certain irregula…
Conjectureopenout-of-distribution-detection statistical-depth uncertainty-quantificationarXiv posted 2 days ago
0 votes0 replies0 views
The conjecture on GROOS methods for out-of-distribution datasets
GROOS selection conjecture. Centered GROOS tends to perform better on mildly OOD datasets such as CIFAR100, Aircraft, and Fruits, whereas the simpler MinDist model might be a bette…
Conjectureopenfew-shot-learning out-of-distribution-detection representation-learningarXiv posted 2 days ago

The K-means/center stability conjecture for statistical depth-based uncertainty scores