Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002922> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4386002922 endingPage "119542" @default.
- W4386002922 startingPage "119542" @default.
- W4386002922 abstract "Classification tasks in 3D point clouds often assume that class events are independent and identically distributed (IID), although this assumption destroys the correlation between classes. This study proposes a classification strategy, Joint Graph Entropy Knowledge Distillation (JGEKD), suitable for non-independent and identically distributed 3D point cloud data, which achieves knowledge transfer of class correlations through knowledge distillation by constructing a loss function based on joint graph entropy. First, we employ joint graphs to capture addthe hidden relationships between classes and implement knowledge distillation to train our model by calculating the entropy of addadd graph. Subsequently, to handle 3D point clouds invariant to spatial transformations, we construct Siamese structures and develop two frameworks, self-knowledge distillation and teacher-knowledge distillation, to facilitate information transfer between different transformation forms of the same data. In addition, we use the above framework to achieve knowledge transfer between point clouds and their corrupted forms, and increase the robustness against corruption of model. Extensive experiments on ScanObject, ModelNet40, ScanntV2_cls and ModelNet-C demonstrate that the proposed strategy can achieve competitive results." @default.
- W4386002922 created "2023-08-20" @default.
- W4386002922 creator A5013618345 @default.
- W4386002922 creator A5022429448 @default.
- W4386002922 creator A5028255512 @default.
- W4386002922 creator A5044470498 @default.
- W4386002922 date "2023-11-01" @default.
- W4386002922 modified "2023-10-12" @default.
- W4386002922 title "Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptions" @default.
- W4386002922 cites W2890018557 @default.
- W4386002922 cites W2978725006 @default.
- W4386002922 cites W2979750740 @default.
- W4386002922 cites W3023371261 @default.
- W4386002922 cites W3024045805 @default.
- W4386002922 cites W3118969708 @default.
- W4386002922 cites W3153465022 @default.
- W4386002922 cites W4281845676 @default.
- W4386002922 cites W4296425714 @default.
- W4386002922 cites W4304182941 @default.
- W4386002922 cites W4307055858 @default.
- W4386002922 cites W4318563497 @default.
- W4386002922 cites W4323660286 @default.
- W4386002922 doi "https://doi.org/10.1016/j.ins.2023.119542" @default.
- W4386002922 hasPublicationYear "2023" @default.
- W4386002922 type Work @default.
- W4386002922 citedByCount "0" @default.
- W4386002922 crossrefType "journal-article" @default.
- W4386002922 hasAuthorship W4386002922A5013618345 @default.
- W4386002922 hasAuthorship W4386002922A5022429448 @default.
- W4386002922 hasAuthorship W4386002922A5028255512 @default.
- W4386002922 hasAuthorship W4386002922A5044470498 @default.
- W4386002922 hasConcept C104317684 @default.
- W4386002922 hasConcept C105795698 @default.
- W4386002922 hasConcept C106301342 @default.
- W4386002922 hasConcept C121332964 @default.
- W4386002922 hasConcept C122123141 @default.
- W4386002922 hasConcept C124101348 @default.
- W4386002922 hasConcept C131979681 @default.
- W4386002922 hasConcept C132525143 @default.
- W4386002922 hasConcept C141513077 @default.
- W4386002922 hasConcept C154945302 @default.
- W4386002922 hasConcept C178790620 @default.
- W4386002922 hasConcept C185592680 @default.
- W4386002922 hasConcept C204030448 @default.
- W4386002922 hasConcept C33923547 @default.
- W4386002922 hasConcept C41008148 @default.
- W4386002922 hasConcept C55493867 @default.
- W4386002922 hasConcept C62520636 @default.
- W4386002922 hasConcept C63479239 @default.
- W4386002922 hasConcept C80444323 @default.
- W4386002922 hasConceptScore W4386002922C104317684 @default.
- W4386002922 hasConceptScore W4386002922C105795698 @default.
- W4386002922 hasConceptScore W4386002922C106301342 @default.
- W4386002922 hasConceptScore W4386002922C121332964 @default.
- W4386002922 hasConceptScore W4386002922C122123141 @default.
- W4386002922 hasConceptScore W4386002922C124101348 @default.
- W4386002922 hasConceptScore W4386002922C131979681 @default.
- W4386002922 hasConceptScore W4386002922C132525143 @default.
- W4386002922 hasConceptScore W4386002922C141513077 @default.
- W4386002922 hasConceptScore W4386002922C154945302 @default.
- W4386002922 hasConceptScore W4386002922C178790620 @default.
- W4386002922 hasConceptScore W4386002922C185592680 @default.
- W4386002922 hasConceptScore W4386002922C204030448 @default.
- W4386002922 hasConceptScore W4386002922C33923547 @default.
- W4386002922 hasConceptScore W4386002922C41008148 @default.
- W4386002922 hasConceptScore W4386002922C55493867 @default.
- W4386002922 hasConceptScore W4386002922C62520636 @default.
- W4386002922 hasConceptScore W4386002922C63479239 @default.
- W4386002922 hasConceptScore W4386002922C80444323 @default.
- W4386002922 hasLocation W43860029221 @default.
- W4386002922 hasOpenAccess W4386002922 @default.
- W4386002922 hasPrimaryLocation W43860029221 @default.
- W4386002922 hasRelatedWork W1717256175 @default.
- W4386002922 hasRelatedWork W1979026279 @default.
- W4386002922 hasRelatedWork W2187758569 @default.
- W4386002922 hasRelatedWork W2323735050 @default.
- W4386002922 hasRelatedWork W2328455322 @default.
- W4386002922 hasRelatedWork W2347733609 @default.
- W4386002922 hasRelatedWork W2936725271 @default.
- W4386002922 hasRelatedWork W3004218185 @default.
- W4386002922 hasRelatedWork W3099502074 @default.
- W4386002922 hasRelatedWork W4245457074 @default.
- W4386002922 hasVolume "648" @default.
- W4386002922 isParatext "false" @default.
- W4386002922 isRetracted "false" @default.
- W4386002922 workType "article" @default.