Pith. sign in

New insights on reducing abrupt representation change in online continual learning

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.CV 1

years

2024 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

support 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Memory-efficient Continual Learning with Neural Collapse Contrastive cs.CV · 2024-12-03 · conditional · none · ref 4

    A continual learning method that combines focal contrastive learning with fixed neural-collapse prototypes and a distillation loss achieves state-of-the-art accuracy in memory-free class- and task-incremental learning.