Back to Search Start Over

VI-PANN: Harnessing Transfer Learning and Uncertainty-Aware Variational Inference for Improved Generalization in Audio Pattern Recognition

Authors :
Fischer, John
Orescanin, Marko
Eckstrand, Eric
Source :
IEEE Access (2024)
Publication Year :
2024

Abstract

Transfer learning (TL) is an increasingly popular approach to training deep learning (DL) models that leverages the knowledge gained by training a foundation model on diverse, large-scale datasets for use on downstream tasks where less domain- or task-specific data is available. The literature is rich with TL techniques and applications; however, the bulk of the research makes use of deterministic DL models which are often uncalibrated and lack the ability to communicate a measure of epistemic (model) uncertainty in prediction. Unlike their deterministic counterparts, Bayesian DL (BDL) models are often well-calibrated, provide access to epistemic uncertainty for a prediction, and are capable of achieving competitive predictive performance. In this study, we propose variational inference pre-trained audio neural networks (VI-PANNs). VI-PANNs are a variational inference variant of the popular ResNet-54 architecture which are pre-trained on AudioSet, a large-scale audio event detection dataset. We evaluate the quality of the resulting uncertainty when transferring knowledge from VI-PANNs to other downstream acoustic classification tasks using the ESC-50, UrbanSound8K, and DCASE2013 datasets. We demonstrate, for the first time, that it is possible to transfer calibrated uncertainty information along with knowledge from upstream tasks to enhance a model's capability to perform downstream tasks.<br />Comment: Published in IEEE Access

Details

Database :
arXiv
Journal :
IEEE Access (2024)
Publication Type :
Report
Accession number :
edsarx.2401.05531
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/ACCESS.2024.3372423