CALA learns a class-specific logit correction from fake incremental tasks and applies it to real new classes, giving small accuracy gains on three FSCIL benchmarks.
Learning imbalanced datasets with label- distribution-aware margin loss
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.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning
CALA learns a class-specific logit correction from fake incremental tasks and applies it to real new classes, giving small accuracy gains on three FSCIL benchmarks.