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.
Incremental Learning of Acoustic Scenes and Sound Events
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we propose a method for incremental learning of two distinct tasks over time: acoustic scene classification (ASC) and audio tagging (AT). We use a simple convolutional neural network (CNN) model as an incremental learner to solve the tasks. Generally, incremental learning methods catastrophically forget the previous task when sequentially trained on a new task. To alleviate this problem, we propose independent learning and knowledge distillation (KD) between the timesteps in learning. Experiments are performed on TUT 2016/2017 dataset, containing 4 acoustic scene classes and 25 sound event classes. The proposed incremental learner first solves the ASC task with an accuracy of 94.0%. Next, it learns to solve the AT task with an F1 score of 54.4%. At the same time, its performance on the previous ASC task decreases only by 5.1 percentage points due to the additional learning of the AT task.
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.