Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/134389
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nguyen, C. | - |
dc.contributor.author | Do, T.-T. | - |
dc.contributor.author | Carneiro, G. | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023; 45(1):841-851 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.issn | 1939-3539 | - |
dc.identifier.uri | https://hdl.handle.net/2440/134389 | - |
dc.description | Published January 2023 | - |
dc.description.abstract | We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single-task setting to the meta-learning multiple-task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well-calibrated and accurate, with state-of-the-art calibration errors while still being competitive on classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks. | - |
dc.description.statementofresponsibility | Cuong Nguyen, Thanh-Toan Do, and Gustavo Carneiro | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.rights | © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. | - |
dc.source.uri | http://dx.doi.org/10.1109/tpami.2022.3147798 | - |
dc.subject | PAC Bayes; meta-learning; few-shot learning; transfer learning | - |
dc.title | PAC-Bayes meta-learning with implicit task-specific posteriors | - |
dc.type | Journal article | - |
dc.identifier.doi | 10.1109/TPAMI.2022.3147798 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/CE140100016 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/DP180103232 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FT190100525 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Nguyen, C. [0000-0003-2672-6291] | - |
dc.identifier.orcid | Carneiro, G. [0000-0002-5571-6220] | - |
Appears in Collections: | 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.