In an exact-fit linear regime with i.i.d. tasks from distribution Π, forgetting obeys a recursive spectral operator whose asymptotic convergence rate is governed by geometric properties of Π.
Online continual learning in image classification: An empirical survey
3 Pith papers cite this work, alongside 381 external citations. Polarity classification is still indexing.
3
Pith papers citing it
381
external citations · Crossref
fields
cs.LG 3representative citing papers
BiCyc aligns old and new class representations bidirectionally with cycle consistency to preserve classification decisions and mitigate forgetting in exemplar-free continual learning.
OCAR combines experience replay with K-FAC Fisher preconditioning and scheduled damping to improve stability and plasticity in online continual learning.
citing papers explorer
-
From Order to Distribution: A Spectral Characterization of Forgetting in Continual Learning
In an exact-fit linear regime with i.i.d. tasks from distribution Π, forgetting obeys a recursive spectral operator whose asymptotic convergence rate is governed by geometric properties of Π.
-
Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
BiCyc aligns old and new class representations bidirectionally with cycle consistency to preserve classification decisions and mitigate forgetting in exemplar-free continual learning.