A distance-threshold rule over base-class prototypes, calibrated to a chosen forgetting rate, improves new-class accuracy in one-shot class-incremental learning while trading a controlled amount of base-class accuracy.
Large scale visual food recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning
A distance-threshold rule over base-class prototypes, calibrated to a chosen forgetting rate, improves new-class accuracy in one-shot class-incremental learning while trading a controlled amount of base-class accuracy.