DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Yanbin | ko |
dc.contributor.author | Lee, Juho | ko |
dc.contributor.author | Park, Minseop | ko |
dc.contributor.author | Kim, Saehoon | ko |
dc.contributor.author | Yang, Eunho | ko |
dc.contributor.author | Hwang, Sung Ju | ko |
dc.contributor.author | Yang, Yi | ko |
dc.date.accessioned | 2020-01-23T07:20:54Z | - |
dc.date.available | 2020-01-23T07:20:54Z | - |
dc.date.created | 2019-11-22 | - |
dc.date.created | 2019-11-22 | - |
dc.date.created | 2019-11-22 | - |
dc.date.issued | 2019-05-06 | - |
dc.identifier.citation | 7th International Conference on Learning Representations, ICLR 2019 | - |
dc.identifier.uri | http://hdl.handle.net/10203/271826 | - |
dc.description.abstract | The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances, by learning a graph construction module that exploits the manifold structure in the data. TPN jointly learns both the parameters of feature embedding and the graph construction in an end-to-end manner. We validate TPN on multiple benchmark datasets, on which it largely outperforms existing few-shot learning approaches and achieves the state-of-the-art results. | - |
dc.language | English | - |
dc.publisher | International Conference on Learning Representations, ICLR | - |
dc.title | Learning to propagate labels: Transductive propagation network for few-shot learning | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85083950649 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 7th International Conference on Learning Representations, ICLR 2019 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Ernest N. Morial Convention Center, New Orleans | - |
dc.contributor.localauthor | Lee, Juho | - |
dc.contributor.localauthor | Yang, Eunho | - |
dc.contributor.localauthor | Hwang, Sung Ju | - |
dc.contributor.nonIdAuthor | Liu, Yanbin | - |
dc.contributor.nonIdAuthor | Park, Minseop | - |
dc.contributor.nonIdAuthor | Kim, Saehoon | - |
dc.contributor.nonIdAuthor | Yang, Yi | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.