Synthesizing prototypical exemplars and perturbation-based variants enables rehearsal-based continual learning with substantially fewer samples per class than standard coreset methods.
Fecam: Exploiting the heterogeneity of class distributions in exemplar-free continual learning.Ad- vances in Neural Information Processing Systems, 36:6582– 6595
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.