Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312883906> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4312883906 endingPage "557" @default.
- W4312883906 startingPage "541" @default.
- W4312883906 abstract "Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average, or a prototype, and measures the similarity of samples and prototypes by Euclidean distance. In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS). In this framework, we further propose a method utilizing Tikhonov regularization as the filter function for few-shot classification. We conduct several experiments to verify our method utilizing different kernels based on the miniImageNet dataset, tiered-ImageNet dataset and CIFAR-FS dataset. The experimental results show that the proposed model can perform the state-of-the-art. In addition, the experimental results show that the proposed shrinkage method can boost the performance. Source code is available at https://github.com/zhangtao2022/DSFN ." @default.
- W4312883906 created "2023-01-05" @default.
- W4312883906 creator A5034420107 @default.
- W4312883906 creator A5082493702 @default.
- W4312883906 date "2022-01-01" @default.
- W4312883906 modified "2023-10-01" @default.
- W4312883906 title "Kernel Relative-prototype Spectral Filtering for Few-Shot Learning" @default.
- W4312883906 cites W2049065678 @default.
- W4312883906 cites W2115733720 @default.
- W4312883906 cites W2140095548 @default.
- W4312883906 cites W2194321275 @default.
- W4312883906 cites W2798836702 @default.
- W4312883906 cites W2905471643 @default.
- W4312883906 cites W2949879676 @default.
- W4312883906 cites W2962895018 @default.
- W4312883906 cites W2963070905 @default.
- W4312883906 cites W2964105864 @default.
- W4312883906 cites W2964162033 @default.
- W4312883906 cites W2997405397 @default.
- W4312883906 cites W3009081299 @default.
- W4312883906 cites W3034312118 @default.
- W4312883906 cites W3034587791 @default.
- W4312883906 cites W3035102141 @default.
- W4312883906 cites W3035143213 @default.
- W4312883906 cites W3101183984 @default.
- W4312883906 cites W3108878460 @default.
- W4312883906 cites W3110214837 @default.
- W4312883906 cites W3116253690 @default.
- W4312883906 cites W3120387732 @default.
- W4312883906 cites W4211208325 @default.
- W4312883906 cites W4214562728 @default.
- W4312883906 cites W4214764301 @default.
- W4312883906 doi "https://doi.org/10.1007/978-3-031-20044-1_31" @default.
- W4312883906 hasPublicationYear "2022" @default.
- W4312883906 type Work @default.
- W4312883906 citedByCount "3" @default.
- W4312883906 countsByYear W43128839062023 @default.
- W4312883906 crossrefType "book-chapter" @default.
- W4312883906 hasAuthorship W4312883906A5034420107 @default.
- W4312883906 hasAuthorship W4312883906A5082493702 @default.
- W4312883906 hasBestOaLocation W43128839062 @default.
- W4312883906 hasConcept C103278499 @default.
- W4312883906 hasConcept C114614502 @default.
- W4312883906 hasConcept C115961682 @default.
- W4312883906 hasConcept C119857082 @default.
- W4312883906 hasConcept C120174047 @default.
- W4312883906 hasConcept C134306372 @default.
- W4312883906 hasConcept C135252773 @default.
- W4312883906 hasConcept C152442038 @default.
- W4312883906 hasConcept C153180895 @default.
- W4312883906 hasConcept C154945302 @default.
- W4312883906 hasConcept C33923547 @default.
- W4312883906 hasConcept C41008148 @default.
- W4312883906 hasConcept C62799726 @default.
- W4312883906 hasConcept C74193536 @default.
- W4312883906 hasConcept C80884492 @default.
- W4312883906 hasConceptScore W4312883906C103278499 @default.
- W4312883906 hasConceptScore W4312883906C114614502 @default.
- W4312883906 hasConceptScore W4312883906C115961682 @default.
- W4312883906 hasConceptScore W4312883906C119857082 @default.
- W4312883906 hasConceptScore W4312883906C120174047 @default.
- W4312883906 hasConceptScore W4312883906C134306372 @default.
- W4312883906 hasConceptScore W4312883906C135252773 @default.
- W4312883906 hasConceptScore W4312883906C152442038 @default.
- W4312883906 hasConceptScore W4312883906C153180895 @default.
- W4312883906 hasConceptScore W4312883906C154945302 @default.
- W4312883906 hasConceptScore W4312883906C33923547 @default.
- W4312883906 hasConceptScore W4312883906C41008148 @default.
- W4312883906 hasConceptScore W4312883906C62799726 @default.
- W4312883906 hasConceptScore W4312883906C74193536 @default.
- W4312883906 hasConceptScore W4312883906C80884492 @default.
- W4312883906 hasLocation W43128839061 @default.
- W4312883906 hasLocation W43128839062 @default.
- W4312883906 hasOpenAccess W4312883906 @default.
- W4312883906 hasPrimaryLocation W43128839061 @default.
- W4312883906 hasRelatedWork W1981015757 @default.
- W4312883906 hasRelatedWork W2110459882 @default.
- W4312883906 hasRelatedWork W2112531253 @default.
- W4312883906 hasRelatedWork W2124135342 @default.
- W4312883906 hasRelatedWork W2149030223 @default.
- W4312883906 hasRelatedWork W2335037768 @default.
- W4312883906 hasRelatedWork W2410198229 @default.
- W4312883906 hasRelatedWork W2974128303 @default.
- W4312883906 hasRelatedWork W3027599074 @default.
- W4312883906 hasRelatedWork W3208561927 @default.
- W4312883906 isParatext "false" @default.
- W4312883906 isRetracted "false" @default.
- W4312883906 workType "book-chapter" @default.