Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313546957> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4313546957 abstract "Time series have always raised great interest among scientists due to their multiple applications in real-world problems. In particular, time series classification using deep learning methods has recently attracted much attention and demonstrated remarkable performance. Unfortunately, most of the techniques studied so far assume that a fully-labeled dataset is available for training, a condition that limits the application of these methods in practice. In this paper, we present Cluster Distillation: a technique that leverages all the available data (labeled or unlabeled) for training a deep time series classifier. The method relies on a self-supervised mechanism that generates surrogate labels that guide learning when external supervisory signals are lacking. We create that mechanism by introducing clustering into a Knowledge Distillation framework in which a first neural net (the Teacher) transfers its beliefs about cluster memberships to a second neural net (the Student) which finally performs semi-supervised classification. Preliminary experiments in ten widely used datasets show that training a convolutional neural net (CNN) with the proposed technique leads to promising results, outperforming state-of-the-art methods in several relevant cases. The implementations are available on: ClusterDistillation" @default.
- W4313546957 created "2023-01-06" @default.
- W4313546957 creator A5011907462 @default.
- W4313546957 creator A5038278611 @default.
- W4313546957 date "2022-11-21" @default.
- W4313546957 modified "2023-10-18" @default.
- W4313546957 title "Cluster Distillation: Semi-supervised Time Series Classification through Clustering-based Self-supervision" @default.
- W4313546957 cites W2883725317 @default.
- W4313546957 cites W2887783173 @default.
- W4313546957 cites W2892035503 @default.
- W4313546957 cites W2919115771 @default.
- W4313546957 cites W2963140444 @default.
- W4313546957 cites W2963465221 @default.
- W4313546957 cites W2984353870 @default.
- W4313546957 cites W2988244882 @default.
- W4313546957 cites W3023371261 @default.
- W4313546957 cites W3023534255 @default.
- W4313546957 cites W3048804154 @default.
- W4313546957 cites W3082281389 @default.
- W4313546957 cites W3082416011 @default.
- W4313546957 cites W3137609883 @default.
- W4313546957 cites W3162049936 @default.
- W4313546957 cites W4210616753 @default.
- W4313546957 cites W4300672471 @default.
- W4313546957 doi "https://doi.org/10.1109/sccc57464.2022.10000276" @default.
- W4313546957 hasPublicationYear "2022" @default.
- W4313546957 type Work @default.
- W4313546957 citedByCount "0" @default.
- W4313546957 crossrefType "proceedings-article" @default.
- W4313546957 hasAuthorship W4313546957A5011907462 @default.
- W4313546957 hasAuthorship W4313546957A5038278611 @default.
- W4313546957 hasConcept C119857082 @default.
- W4313546957 hasConcept C124101348 @default.
- W4313546957 hasConcept C153180895 @default.
- W4313546957 hasConcept C154945302 @default.
- W4313546957 hasConcept C178790620 @default.
- W4313546957 hasConcept C185592680 @default.
- W4313546957 hasConcept C204030448 @default.
- W4313546957 hasConcept C41008148 @default.
- W4313546957 hasConcept C50644808 @default.
- W4313546957 hasConcept C73555534 @default.
- W4313546957 hasConcept C81363708 @default.
- W4313546957 hasConcept C95623464 @default.
- W4313546957 hasConceptScore W4313546957C119857082 @default.
- W4313546957 hasConceptScore W4313546957C124101348 @default.
- W4313546957 hasConceptScore W4313546957C153180895 @default.
- W4313546957 hasConceptScore W4313546957C154945302 @default.
- W4313546957 hasConceptScore W4313546957C178790620 @default.
- W4313546957 hasConceptScore W4313546957C185592680 @default.
- W4313546957 hasConceptScore W4313546957C204030448 @default.
- W4313546957 hasConceptScore W4313546957C41008148 @default.
- W4313546957 hasConceptScore W4313546957C50644808 @default.
- W4313546957 hasConceptScore W4313546957C73555534 @default.
- W4313546957 hasConceptScore W4313546957C81363708 @default.
- W4313546957 hasConceptScore W4313546957C95623464 @default.
- W4313546957 hasLocation W43135469571 @default.
- W4313546957 hasOpenAccess W4313546957 @default.
- W4313546957 hasPrimaryLocation W43135469571 @default.
- W4313546957 hasRelatedWork W2175746458 @default.
- W4313546957 hasRelatedWork W2732542196 @default.
- W4313546957 hasRelatedWork W2961085424 @default.
- W4313546957 hasRelatedWork W2964383635 @default.
- W4313546957 hasRelatedWork W2995914718 @default.
- W4313546957 hasRelatedWork W3027997911 @default.
- W4313546957 hasRelatedWork W3093612317 @default.
- W4313546957 hasRelatedWork W4225852842 @default.
- W4313546957 hasRelatedWork W4287776258 @default.
- W4313546957 hasRelatedWork W564581980 @default.
- W4313546957 isParatext "false" @default.
- W4313546957 isRetracted "false" @default.
- W4313546957 workType "article" @default.