Learning to propagate labels: Transductive propagation network for few-shot learning

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 735
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorLiu, Yanbinko
dc.contributor.authorLee, Juhoko
dc.contributor.authorPark, Minseopko
dc.contributor.authorKim, Saehoonko
dc.contributor.authorYang, Eunhoko
dc.contributor.authorHwang, Sung Juko
dc.contributor.authorYang, Yiko
dc.date.accessioned2020-01-23T07:20:54Z-
dc.date.available2020-01-23T07:20:54Z-
dc.date.created2019-11-22-
dc.date.created2019-11-22-
dc.date.created2019-11-22-
dc.date.issued2019-05-06-
dc.identifier.citation7th International Conference on Learning Representations, ICLR 2019-
dc.identifier.urihttp://hdl.handle.net/10203/271826-
dc.description.abstractThe 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.languageEnglish-
dc.publisherInternational Conference on Learning Representations, ICLR-
dc.titleLearning to propagate labels: Transductive propagation network for few-shot learning-
dc.typeConference-
dc.identifier.scopusid2-s2.0-85083950649-
dc.type.rimsCONF-
dc.citation.publicationname7th International Conference on Learning Representations, ICLR 2019-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationErnest N. Morial Convention Center, New Orleans-
dc.contributor.localauthorLee, Juho-
dc.contributor.localauthorYang, Eunho-
dc.contributor.localauthorHwang, Sung Ju-
dc.contributor.nonIdAuthorLiu, Yanbin-
dc.contributor.nonIdAuthorPark, Minseop-
dc.contributor.nonIdAuthorKim, Saehoon-
dc.contributor.nonIdAuthorYang, Yi-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0