The paper formalizes Free-Flow Class-Incremental Learning with variable class arrivals and introduces a class-wise mean loss plus targeted adjustments that reduce performance drops seen in standard CIL methods.
Ad- vances in Neural Information Processing Systems36, 11151–11167 (2024)
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Realistic Class-Incremental Learning with Free-Flow Increments
The paper formalizes Free-Flow Class-Incremental Learning with variable class arrivals and introduces a class-wise mean loss plus targeted adjustments that reduce performance drops seen in standard CIL methods.