DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, Taewon | ko |
dc.contributor.author | Kim, Heeyoung | ko |
dc.date.accessioned | 2022-12-13T07:01:42Z | - |
dc.date.available | 2022-12-13T07:01:42Z | - |
dc.date.created | 2022-12-12 | - |
dc.date.issued | 2020-12-09 | - |
dc.identifier.citation | 34th Conference on Neural Information Processing Systems, NeurIPS 2020 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10203/302929 | - |
dc.description.abstract | We propose a few-shot learning method for detecting out-of-distribution (OOD) samples from classes that are unseen during training while classifying samples from seen classes using only a few labeled examples. For detecting unseen classes while generalizing to new samples of known classes, we synthesize fake samples, i.e., OOD samples, but that resemble in-distribution samples, and use them along with real samples. Our approach is based on an extension of model-agnostic meta learning (MAML) and is denoted as OOD-MAML, which not only learns a model initialization but also the initial fake samples across tasks. The learned initial fake samples can be used to quickly adapt to new tasks to form task-specific fake samples with only one or a few gradient update steps using MAML. For testing, OOD-MAML converts a K-shot N-way classification task into N sub-tasks of K-shot OOD detection with respect to each class. The joint analysis of N sub-tasks facilitates simultaneous classification and OOD detection and, furthermore, offers an advantage, in that it does not require re-training when the number of classes for a test task differs from that for training tasks; it is sufficient to simply assume as many sub-tasks as the number of classes for the test task. We also demonstrate the effective performance of OOD-MAML over benchmark datasets. | - |
dc.language | English | - |
dc.publisher | Conference on Neural Information Processing Systems | - |
dc.title | OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85104041887 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 34th Conference on Neural Information Processing Systems, NeurIPS 2020 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Kim, Heeyoung | - |
dc.contributor.nonIdAuthor | Jeong, Taewon | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.