Synthesizing prototypical exemplars and perturbation-based variants enables rehearsal-based continual learning with substantially fewer samples per class than standard coreset methods.
Con- sequently, synthetic subsets can be generated by perturb- ing samples around the prototype, effectively producing diverse data points from a single exemplar
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Memory-efficient Continual Learning with Prototypical Exemplar Condensation
Synthesizing prototypical exemplars and perturbation-based variants enables rehearsal-based continual learning with substantially fewer samples per class than standard coreset methods.