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.
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 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Memory-efficient Continual Learning with Neural Collapse Contrastive
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.