Fresh-CL combines fixed equiangular classifier targets with mixture-of-experts projections to reduce feature overlap in multi-task continual learning, reporting about 2% average accuracy gain over a strong baseline.
Memory-efficient incremental learning through feature adaptation
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 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
Fresh-CL combines fixed equiangular classifier targets with mixture-of-experts projections to reduce feature overlap in multi-task continual learning, reporting about 2% average accuracy gain over a strong baseline.