Continual MultiPatches (CMP) trains self-supervised online continual learning models on multiple patches of each single example, reaching higher linear probing accuracy than most experience replay baselines without storing any past data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Replay-free Online Continual Learning with Self-Supervised MultiPatches
Continual MultiPatches (CMP) trains self-supervised online continual learning models on multiple patches of each single example, reaching higher linear probing accuracy than most experience replay baselines without storing any past data.