Pith. sign in

Continual evidential deep learning for out- of-distribution detection

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Uncertainty Quantification in Continual Open-World Learning

cs.LG · 2024-12-21 · conditional · novelty 5.0

COUQ iteratively combines old-class and novel-class feature reconstruction errors to produce uncertainty scores that stay reliable as new classes arrive, improving continual novelty detection and active learning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Uncertainty Quantification in Continual Open-World Learning cs.LG · 2024-12-21 · conditional · none · ref 1

    COUQ iteratively combines old-class and novel-class feature reconstruction errors to produce uncertainty scores that stay reliable as new classes arrive, improving continual novelty detection and active learning.