Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384207938> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4384207938 endingPage "109820" @default.
- W4384207938 startingPage "109820" @default.
- W4384207938 abstract "In comparison with support vector data description (SVDD), deep SVDD (DSVDD) is more suitable for dealing with large-scale data sets. DSVDD uses mapping network to replace the role of kernel mapping in SVDD. Moreover, the objective of DSVDD is to simultaneously learn the optimal connection weights of mapping network and the minimum volume of hypersphere. To further improve the performance of DSVDD for tackling large-scale data sets and obtain the discriminative features of the given samples in a self-supervised learning manner, contrastive DSVDD (CDSVDD) is proposed in this study. In the pre-training phase of CDSVDD, the contrastive loss and the rotation prediction loss are jointly minimized to achieve the optimal feature representations. Furthermore, the learned feature representations are utilized to determine the hypersphere center. In the training phase of CDSVDD, the distances between the obtained feature representations and the hypersphere center together with the contrastive loss are simultaneously minimized to derive the optimal network connection weights, the minimum volume of hypersphere and the optimal feature representations. In addition, CDSVDD can efficiently solve the hypersphere collapse problem of DSVDD. The ablation study on CDSVDD verifies that compared with the case of determining the hypersphere center by the feature representations of the original samples, the hypersphere center determined by the feature representations of the augmented samples makes CDSVDD achieve better hypersphere boundary and more compact feature representations. Experimental results on the four benchmark data sets demonstrate that the proposed CDSVDD acquires better detection performance in comparison with its six pertinent methods." @default.
- W4384207938 created "2023-07-14" @default.
- W4384207938 creator A5021797755 @default.
- W4384207938 creator A5084083030 @default.
- W4384207938 date "2023-11-01" @default.
- W4384207938 modified "2023-09-23" @default.
- W4384207938 title "Contrastive deep support vector data description" @default.
- W4384207938 cites W1970088130 @default.
- W4384207938 cites W2112796928 @default.
- W4384207938 cites W2142047467 @default.
- W4384207938 cites W3010795489 @default.
- W4384207938 cites W3037099311 @default.
- W4384207938 cites W3157975240 @default.
- W4384207938 cites W3159911466 @default.
- W4384207938 cites W3193416433 @default.
- W4384207938 cites W4200583727 @default.
- W4384207938 cites W4286776235 @default.
- W4384207938 cites W4290964450 @default.
- W4384207938 cites W4308344394 @default.
- W4384207938 doi "https://doi.org/10.1016/j.patcog.2023.109820" @default.
- W4384207938 hasPublicationYear "2023" @default.
- W4384207938 type Work @default.
- W4384207938 citedByCount "0" @default.
- W4384207938 crossrefType "journal-article" @default.
- W4384207938 hasAuthorship W4384207938A5021797755 @default.
- W4384207938 hasAuthorship W4384207938A5084083030 @default.
- W4384207938 hasConcept C114614502 @default.
- W4384207938 hasConcept C12267149 @default.
- W4384207938 hasConcept C13280743 @default.
- W4384207938 hasConcept C138885662 @default.
- W4384207938 hasConcept C153180895 @default.
- W4384207938 hasConcept C154945302 @default.
- W4384207938 hasConcept C185798385 @default.
- W4384207938 hasConcept C205649164 @default.
- W4384207938 hasConcept C2776401178 @default.
- W4384207938 hasConcept C2776562905 @default.
- W4384207938 hasConcept C33923547 @default.
- W4384207938 hasConcept C41008148 @default.
- W4384207938 hasConcept C41895202 @default.
- W4384207938 hasConcept C74193536 @default.
- W4384207938 hasConcept C83665646 @default.
- W4384207938 hasConcept C97931131 @default.
- W4384207938 hasConceptScore W4384207938C114614502 @default.
- W4384207938 hasConceptScore W4384207938C12267149 @default.
- W4384207938 hasConceptScore W4384207938C13280743 @default.
- W4384207938 hasConceptScore W4384207938C138885662 @default.
- W4384207938 hasConceptScore W4384207938C153180895 @default.
- W4384207938 hasConceptScore W4384207938C154945302 @default.
- W4384207938 hasConceptScore W4384207938C185798385 @default.
- W4384207938 hasConceptScore W4384207938C205649164 @default.
- W4384207938 hasConceptScore W4384207938C2776401178 @default.
- W4384207938 hasConceptScore W4384207938C2776562905 @default.
- W4384207938 hasConceptScore W4384207938C33923547 @default.
- W4384207938 hasConceptScore W4384207938C41008148 @default.
- W4384207938 hasConceptScore W4384207938C41895202 @default.
- W4384207938 hasConceptScore W4384207938C74193536 @default.
- W4384207938 hasConceptScore W4384207938C83665646 @default.
- W4384207938 hasConceptScore W4384207938C97931131 @default.
- W4384207938 hasFunder F4320321001 @default.
- W4384207938 hasFunder F4320322163 @default.
- W4384207938 hasFunder F4320324851 @default.
- W4384207938 hasLocation W43842079381 @default.
- W4384207938 hasOpenAccess W4384207938 @default.
- W4384207938 hasPrimaryLocation W43842079381 @default.
- W4384207938 hasRelatedWork W1461621550 @default.
- W4384207938 hasRelatedWork W2020350089 @default.
- W4384207938 hasRelatedWork W2119772606 @default.
- W4384207938 hasRelatedWork W2378448154 @default.
- W4384207938 hasRelatedWork W2729514902 @default.
- W4384207938 hasRelatedWork W2773500201 @default.
- W4384207938 hasRelatedWork W2890505431 @default.
- W4384207938 hasRelatedWork W2944661354 @default.
- W4384207938 hasRelatedWork W2970216048 @default.
- W4384207938 hasRelatedWork W2187500075 @default.
- W4384207938 hasVolume "143" @default.
- W4384207938 isParatext "false" @default.
- W4384207938 isRetracted "false" @default.
- W4384207938 workType "article" @default.