An incremental learning method with MSE distillation lets a SELD model add four new sound classes after eight while roughly matching the performance of a model trained on all twelve at once.
Maximum likelihood approach to “informed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Class-Incremental Learning for Sound Event Localization and Detection
An incremental learning method with MSE distillation lets a SELD model add four new sound classes after eight while roughly matching the performance of a model trained on all twelve at once.