FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209279086> ?p ?o ?g. }

• W3209279086 abstract "Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision. However, they are less successful in domains without established data transformations such as time series data. In this paper, we propose a novel self-supervised learning framework that combines contrastive learning with neural processes. It relies on recent advances in neural processes to perform time series forecasting. This allows to generate augmented versions of data by employing a set of various sampling functions and, hence, avoid manually designed augmentations. We extend conventional neural processes and propose a new contrastive loss to learn times series representations in a self-supervised setup. Therefore, unlike previous self-supervised methods, our augmentation pipeline is task-agnostic, enabling our method to perform well across various applications. In particular, a ResNet with a linear classifier trained using our approach is able to outperform state-of-the-art techniques across industrial, medical and audio datasets improving accuracy over 10% in ECG periodic data. We further demonstrate that our self-supervised representations are more efficient in the latent space, improving multiple clustering indexes and that fine-tuning our method on 10% of labels achieves results competitive to fully-supervised learning." @default.
• W3209279086 created "2021-11-08" @default.
• W3209279086 creator A5006012153 @default.
• W3209279086 creator A5026912892 @default.
• W3209279086 creator A5062981565 @default.
• W3209279086 creator A5063952313 @default.
• W3209279086 creator A5068329095 @default.
• W3209279086 date "2021-10-24" @default.
• W3209279086 modified "2023-09-27" @default.
• W3209279086 title "Contrastive Neural Processes for Self-Supervised Learning" @default.
• W3209279086 cites W1790904062 @default.
• W3209279086 cites W2012079387 @default.
• W3209279086 cites W2019505419 @default.
• W3209279086 cites W2028899550 @default.
• W3209279086 cites W2038484192 @default.
• W3209279086 cites W2123958887 @default.
• W3209279086 cites W2131571251 @default.
• W3209279086 cites W2152790380 @default.
• W3209279086 cites W2157364932 @default.
• W3209279086 cites W2162800060 @default.
• W3209279086 cites W2593116425 @default.
• W3209279086 cites W2842511635 @default.
• W3209279086 cites W2910612230 @default.
• W3209279086 cites W2920777619 @default.
• W3209279086 cites W2936774411 @default.
• W3209279086 cites W2944828972 @default.
• W3209279086 cites W2962908092 @default.
• W3209279086 cites W2971155163 @default.
• W3209279086 cites W2995489995 @default.
• W3209279086 cites W2995554883 @default.
• W3209279086 cites W3005680577 @default.
• W3209279086 cites W3010094231 @default.
• W3209279086 cites W3035058308 @default.
• W3209279086 cites W3035164673 @default.
• W3209279086 cites W3035524453 @default.
• W3209279086 cites W3044308976 @default.
• W3209279086 cites W3092101822 @default.
• W3209279086 cites W3095121901 @default.
• W3209279086 cites W3100859887 @default.
• W3209279086 cites W3101821705 @default.
• W3209279086 cites W3107490265 @default.
• W3209279086 cites W3123465393 @default.
• W3209279086 cites W3134486096 @default.
• W3209279086 cites W3165998135 @default.
• W3209279086 hasPublicationYear "2021" @default.
• W3209279086 type Work @default.
• W3209279086 sameAs 3209279086 @default.
• W3209279086 citedByCount "0" @default.
• W3209279086 crossrefType "posted-content" @default.
• W3209279086 hasAuthorship W3209279086A5006012153 @default.
• W3209279086 hasAuthorship W3209279086A5026912892 @default.
• W3209279086 hasAuthorship W3209279086A5062981565 @default.
• W3209279086 hasAuthorship W3209279086A5063952313 @default.
• W3209279086 hasAuthorship W3209279086A5068329095 @default.
• W3209279086 hasConcept C119857082 @default.
• W3209279086 hasConcept C136389625 @default.
• W3209279086 hasConcept C153180895 @default.
• W3209279086 hasConcept C154945302 @default.
• W3209279086 hasConcept C177264268 @default.
• W3209279086 hasConcept C199360897 @default.
• W3209279086 hasConcept C41008148 @default.
• W3209279086 hasConcept C43521106 @default.
• W3209279086 hasConcept C50644808 @default.
• W3209279086 hasConcept C73555534 @default.
• W3209279086 hasConcept C95623464 @default.
• W3209279086 hasConceptScore W3209279086C119857082 @default.
• W3209279086 hasConceptScore W3209279086C136389625 @default.
• W3209279086 hasConceptScore W3209279086C153180895 @default.
• W3209279086 hasConceptScore W3209279086C154945302 @default.
• W3209279086 hasConceptScore W3209279086C177264268 @default.
• W3209279086 hasConceptScore W3209279086C199360897 @default.
• W3209279086 hasConceptScore W3209279086C41008148 @default.
• W3209279086 hasConceptScore W3209279086C43521106 @default.
• W3209279086 hasConceptScore W3209279086C50644808 @default.
• W3209279086 hasConceptScore W3209279086C73555534 @default.
• W3209279086 hasConceptScore W3209279086C95623464 @default.
• W3209279086 hasLocation W32092790861 @default.
• W3209279086 hasOpenAccess W3209279086 @default.
• W3209279086 hasPrimaryLocation W32092790861 @default.
• W3209279086 hasRelatedWork W2258852083 @default.
• W3209279086 hasRelatedWork W2962764460 @default.
• W3209279086 hasRelatedWork W2963465221 @default.
• W3209279086 hasRelatedWork W3034978746 @default.
• W3209279086 hasRelatedWork W3037584823 @default.
• W3209279086 hasRelatedWork W3086580107 @default.
• W3209279086 hasRelatedWork W3099025572 @default.
• W3209279086 hasRelatedWork W3100010556 @default.
• W3209279086 hasRelatedWork W3113614523 @default.
• W3209279086 hasRelatedWork W3118582944 @default.
• W3209279086 hasRelatedWork W3122924117 @default.
• W3209279086 hasRelatedWork W3124328990 @default.
• W3209279086 hasRelatedWork W3127664874 @default.
• W3209279086 hasRelatedWork W3130223764 @default.
• W3209279086 hasRelatedWork W3131512583 @default.
• W3209279086 hasRelatedWork W3153597994 @default.
• W3209279086 hasRelatedWork W3160530883 @default.
• W3209279086 hasRelatedWork W3170752662 @default.
• W3209279086 hasRelatedWork W3172122903 @default.
• W3209279086 hasRelatedWork W3177393777 @default.
• W3209279086 isParatext "false" @default.

• next