Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366999718> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W4366999718 abstract "Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes of methods, prototype-based and graph-based, have the disadvantages of inaccurate prototype estimation and sub-optimal graph construction with kernel functions, respectively. In this paper, we propose a novel prototype-based label propagation to solve these issues. Specifically, our graph construction is based on the relation between prototypes and samples rather than between samples. As prototypes are being updated, the graph changes. We also estimate the label of each prototype instead of considering a prototype be the class centre. On mini-ImageNet, tiered-ImageNet, CIFAR-FS and CUB datasets, we show the proposed method outperforms other state-of-the-art methods in transductive FSL and semi-supervised FSL when some unlabeled data accompanies the novel few-shot task." @default.
- W4366999718 created "2023-04-27" @default.
- W4366999718 creator A5002212263 @default.
- W4366999718 creator A5035976373 @default.
- W4366999718 date "2023-04-23" @default.
- W4366999718 modified "2023-09-24" @default.
- W4366999718 title "Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement" @default.
- W4366999718 doi "https://doi.org/10.48550/arxiv.2304.11598" @default.
- W4366999718 hasPublicationYear "2023" @default.
- W4366999718 type Work @default.
- W4366999718 citedByCount "0" @default.
- W4366999718 crossrefType "posted-content" @default.
- W4366999718 hasAuthorship W4366999718A5002212263 @default.
- W4366999718 hasAuthorship W4366999718A5035976373 @default.
- W4366999718 hasBestOaLocation W43669997181 @default.
- W4366999718 hasConcept C119857082 @default.
- W4366999718 hasConcept C132525143 @default.
- W4366999718 hasConcept C153083717 @default.
- W4366999718 hasConcept C153180895 @default.
- W4366999718 hasConcept C154945302 @default.
- W4366999718 hasConcept C41008148 @default.
- W4366999718 hasConcept C51632099 @default.
- W4366999718 hasConcept C80444323 @default.
- W4366999718 hasConceptScore W4366999718C119857082 @default.
- W4366999718 hasConceptScore W4366999718C132525143 @default.
- W4366999718 hasConceptScore W4366999718C153083717 @default.
- W4366999718 hasConceptScore W4366999718C153180895 @default.
- W4366999718 hasConceptScore W4366999718C154945302 @default.
- W4366999718 hasConceptScore W4366999718C41008148 @default.
- W4366999718 hasConceptScore W4366999718C51632099 @default.
- W4366999718 hasConceptScore W4366999718C80444323 @default.
- W4366999718 hasLocation W43669997181 @default.
- W4366999718 hasOpenAccess W4366999718 @default.
- W4366999718 hasPrimaryLocation W43669997181 @default.
- W4366999718 hasRelatedWork W1965249131 @default.
- W4366999718 hasRelatedWork W2905233337 @default.
- W4366999718 hasRelatedWork W2919053476 @default.
- W4366999718 hasRelatedWork W2995253937 @default.
- W4366999718 hasRelatedWork W3013366130 @default.
- W4366999718 hasRelatedWork W3043252291 @default.
- W4366999718 hasRelatedWork W3099765033 @default.
- W4366999718 hasRelatedWork W3174891612 @default.
- W4366999718 hasRelatedWork W3204277253 @default.
- W4366999718 hasRelatedWork W4245873437 @default.
- W4366999718 isParatext "false" @default.
- W4366999718 isRetracted "false" @default.
- W4366999718 workType "article" @default.