Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015873263> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3015873263 endingPage "105837" @default.
- W3015873263 startingPage "105837" @default.
- W3015873263 abstract "Abstract In this work, we reveal an essential problem rarely discussed in current semi-supervised learning literatures: the learned feature distribution mismatch problem between labeled samples and unlabeled samples. It is common knowledge that learning from the limited labeled data easily leads to overfitting. However, the difference between the inferred labels of unlabeled data and the ground truths of labeled data may make the learned features of labeled and unlabeled data have different distributions. This distribution mismatch problem may destroy the assumption of smoothness widely used in semi-supervised field, resulting in unsatisfactory performance. In this paper, we propose a novel Semi-supervised Dual-Branch Network (SDB-Net), in which the first branch is trained with labeled and unlabeled data, and the other is trained with the predictions of unlabeled data generated from the first branch only. To avoid the different distributions between ground-truth labels and inferred labels for the unlabeled data, we proposed an effective co-consistency loss to overcome the mismatch problem and a mix-consistency loss to make each branch learn a consistent feature representation. Meanwhile, we designed an augmentation supervised loss for the first branch to further alleviate the mismatch problem. With the designed three kinds of losses, the proposed SDB-Net can be efficiently trained. The experimental results on three benchmark datasets, such as CIFAR-10, CIFAR-100 and SVHN, show the superior performance of the proposed SDB-Net." @default.
- W3015873263 created "2020-04-17" @default.
- W3015873263 creator A5037873810 @default.
- W3015873263 creator A5038362365 @default.
- W3015873263 creator A5055451172 @default.
- W3015873263 date "2020-06-01" @default.
- W3015873263 modified "2023-10-17" @default.
- W3015873263 title "Semi-supervised Dual-Branch Network for image classification" @default.
- W3015873263 cites W2117539524 @default.
- W3015873263 cites W2768975974 @default.
- W3015873263 cites W2895094948 @default.
- W3015873263 cites W2895771689 @default.
- W3015873263 cites W2902479064 @default.
- W3015873263 cites W2903121843 @default.
- W3015873263 cites W2928496594 @default.
- W3015873263 cites W2963351448 @default.
- W3015873263 cites W2964159205 @default.
- W3015873263 cites W2979744195 @default.
- W3015873263 cites W2979805229 @default.
- W3015873263 cites W2981571980 @default.
- W3015873263 cites W3209458476 @default.
- W3015873263 doi "https://doi.org/10.1016/j.knosys.2020.105837" @default.
- W3015873263 hasPublicationYear "2020" @default.
- W3015873263 type Work @default.
- W3015873263 sameAs 3015873263 @default.
- W3015873263 citedByCount "8" @default.
- W3015873263 countsByYear W30158732632021 @default.
- W3015873263 countsByYear W30158732632022 @default.
- W3015873263 countsByYear W30158732632023 @default.
- W3015873263 crossrefType "journal-article" @default.
- W3015873263 hasAuthorship W3015873263A5037873810 @default.
- W3015873263 hasAuthorship W3015873263A5038362365 @default.
- W3015873263 hasAuthorship W3015873263A5055451172 @default.
- W3015873263 hasConcept C115961682 @default.
- W3015873263 hasConcept C124952713 @default.
- W3015873263 hasConcept C142362112 @default.
- W3015873263 hasConcept C153180895 @default.
- W3015873263 hasConcept C154945302 @default.
- W3015873263 hasConcept C2780980858 @default.
- W3015873263 hasConcept C31972630 @default.
- W3015873263 hasConcept C41008148 @default.
- W3015873263 hasConceptScore W3015873263C115961682 @default.
- W3015873263 hasConceptScore W3015873263C124952713 @default.
- W3015873263 hasConceptScore W3015873263C142362112 @default.
- W3015873263 hasConceptScore W3015873263C153180895 @default.
- W3015873263 hasConceptScore W3015873263C154945302 @default.
- W3015873263 hasConceptScore W3015873263C2780980858 @default.
- W3015873263 hasConceptScore W3015873263C31972630 @default.
- W3015873263 hasConceptScore W3015873263C41008148 @default.
- W3015873263 hasFunder F4320321001 @default.
- W3015873263 hasFunder F4320321921 @default.
- W3015873263 hasFunder F4320322769 @default.
- W3015873263 hasFunder F4320334898 @default.
- W3015873263 hasFunder F4320335787 @default.
- W3015873263 hasLocation W30158732631 @default.
- W3015873263 hasOpenAccess W3015873263 @default.
- W3015873263 hasPrimaryLocation W30158732631 @default.
- W3015873263 hasRelatedWork W2005185696 @default.
- W3015873263 hasRelatedWork W2092957489 @default.
- W3015873263 hasRelatedWork W2130228941 @default.
- W3015873263 hasRelatedWork W2132132164 @default.
- W3015873263 hasRelatedWork W2161229648 @default.
- W3015873263 hasRelatedWork W2235753890 @default.
- W3015873263 hasRelatedWork W2314419244 @default.
- W3015873263 hasRelatedWork W2366116130 @default.
- W3015873263 hasRelatedWork W2889893736 @default.
- W3015873263 hasRelatedWork W2993674027 @default.
- W3015873263 hasVolume "197" @default.
- W3015873263 isParatext "false" @default.
- W3015873263 isRetracted "false" @default.
- W3015873263 magId "3015873263" @default.
- W3015873263 workType "article" @default.