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

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

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 ri...

Full description

Bibliographic Details
Main Authors: John Fischer, Marko Orescanin, Eric Eckstrand
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Audio event detection
AudioSet
Bayesian deep learning
transfer learning
uncertainty decomposition
uncertainty quantification
Online Access:https://ieeexplore.ieee.org/document/10456907/

Internet

https://ieeexplore.ieee.org/document/10456907/

Similar Items