Continual Learning For On-Device Environmental Sound Classification
This addresses the challenge of incremental learning for resource-constrained devices, offering a domain-specific solution for environmental sound classification.
The paper tackles the problem of catastrophic forgetting in on-device environmental sound classification by proposing a continual learning method that selects historical data based on per-sample classification uncertainty, achieving improved accuracy and computational efficiency on DCASE 2019 Task 1 and ESC-50 datasets.
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this issue, we propose a simple and efficient continual learning method. Our method selects the historical data for the training by measuring the per-sample classification uncertainty. Specifically, we measure the uncertainty by observing how the classification probability of data fluctuates against the parallel perturbations added to the classifier embedding. In this way, the computation cost can be significantly reduced compared with adding perturbation to the raw data. Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification.