Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/128993
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Uncertainty in model-agnostic meta-learning using variational inference |
Author: | Nguyen, C. Do, T.T. Carneiro, G. |
Citation: | Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV 2020), 2020, pp.3079-3089 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2020 |
Series/Report no.: | IEEE Winter Conference on Applications of Computer Vision |
ISBN: | 9781728165530 |
ISSN: | 2472-6737 2642-9381 |
Conference Name: | The IEEE Winter Conference on Applications of Computer Vision (WACV) (1 Mar 2020 - 5 Mar 2020 : Snowmass Village, Colorado, USA) |
Statement of Responsibility: | Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro |
Abstract: | We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning. The proposed algorithm employs a gradient-based variational inference to infer the posterior of model parameters to a new task. Our algorithm can be applied to any model architecture and can be implemented in various machine learning paradigms, including regression and classification. We show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on two few-shot classification benchmarks (Omniglot and Mini-ImageNet), and competitive results in a multi-modal task-distribution regression. |
Keywords: | stat.ML |
Rights: | ©2020 IEEE |
DOI: | 10.1109/WACV45572.2020.9093536 |
Grant ID: | http://purl.org/au-research/grants/arc/DP180103232 http://purl.org/au-research/grants/arc/CE140100016 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/9087828/proceeding |
Appears in Collections: | Aurora harvest 4 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.