FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W582055897> ?p ?o ?g. }

• W582055897 abstract "Deep neural networks trained on large-scale dataset can learn transferable features that promote learning multiple tasks for inductive transfer and labeling mitigation. As deep features eventually transition from general to specific along the network, a fundamental problem is how to exploit the relationship structure across different tasks while accounting for the feature transferability in the task-specific layers. In this work, we propose a novel Deep Relationship Network (DRN) architecture for multi-task learning by discovering correlated tasks based on multiple task-specific layers of a deep convolutional neural network. DRN models the task relationship by imposing matrix normal priors over the network parameters of all task-specific layers, including higher feature layers and classifier layer that are not transferable safely. By jointly learning the transferable features and task relationships, DRN is able to alleviate the dilemma of negative-transfer in the feature layers and under-transfer in the classifier layer. Empirical evidence shows that DRN yields state-of-the-art classification results on standard multi-domain object recognition datasets." @default.
• W582055897 created "2016-06-24" @default.
• W582055897 creator A5019241553 @default.
• W582055897 creator A5034579434 @default.
• W582055897 creator A5036357902 @default.
• W582055897 date "2015-06-06" @default.
• W582055897 modified "2023-09-25" @default.
• W582055897 title "Learning Multiple Tasks with Deep Relationship Networks" @default.
• W582055897 cites W1520871589 @default.
• W582055897 cites W1722318740 @default.
• W582055897 cites W1896424170 @default.
• W582055897 cites W1939941161 @default.
• W582055897 cites W1978660892 @default.
• W582055897 cites W2018096278 @default.
• W582055897 cites W2028795211 @default.
• W582055897 cites W2065180801 @default.
• W582055897 cites W2097451239 @default.
• W582055897 cites W2102605133 @default.
• W582055897 cites W2107215754 @default.
• W582055897 cites W2110332320 @default.
• W582055897 cites W2130903752 @default.
• W582055897 cites W2143104527 @default.
• W582055897 cites W2145620688 @default.
• W582055897 cites W2155541015 @default.
• W582055897 cites W2158899491 @default.
• W582055897 cites W2163922914 @default.
• W582055897 cites W2184188583 @default.
• W582055897 cites W2186054958 @default.
• W582055897 cites W2199851682 @default.
• W582055897 cites W22861983 @default.
• W582055897 cites W2339391301 @default.
• W582055897 cites W2407277018 @default.
• W582055897 cites W2913340405 @default.
• W582055897 cites W2949201716 @default.
• W582055897 cites W2949667497 @default.
• W582055897 cites W2950094539 @default.
• W582055897 cites W2951084305 @default.
• W582055897 cites W2951670162 @default.
• W582055897 cites W2951882412 @default.
• W582055897 cites W2962835968 @default.
• W582055897 cites W2964121793 @default.
• W582055897 cites W577139289 @default.
• W582055897 hasPublicationYear "2015" @default.
• W582055897 type Work @default.
• W582055897 sameAs 582055897 @default.
• W582055897 citedByCount "49" @default.
• W582055897 countsByYear W5820558972016 @default.
• W582055897 countsByYear W5820558972017 @default.
• W582055897 countsByYear W5820558972018 @default.
• W582055897 countsByYear W5820558972019 @default.
• W582055897 countsByYear W5820558972020 @default.
• W582055897 countsByYear W5820558972021 @default.
• W582055897 crossrefType "posted-content" @default.
• W582055897 hasAuthorship W582055897A5019241553 @default.
• W582055897 hasAuthorship W582055897A5034579434 @default.
• W582055897 hasAuthorship W582055897A5036357902 @default.
• W582055897 hasConcept C108583219 @default.
• W582055897 hasConcept C119857082 @default.
• W582055897 hasConcept C138885662 @default.
• W582055897 hasConcept C140331021 @default.
• W582055897 hasConcept C150899416 @default.
• W582055897 hasConcept C153180895 @default.
• W582055897 hasConcept C154945302 @default.
• W582055897 hasConcept C162324750 @default.
• W582055897 hasConcept C165696696 @default.
• W582055897 hasConcept C187736073 @default.
• W582055897 hasConcept C2776401178 @default.
• W582055897 hasConcept C2780451532 @default.
• W582055897 hasConcept C28006648 @default.
• W582055897 hasConcept C2984842247 @default.
• W582055897 hasConcept C38652104 @default.
• W582055897 hasConcept C41008148 @default.
• W582055897 hasConcept C41895202 @default.
• W582055897 hasConcept C50644808 @default.
• W582055897 hasConcept C59404180 @default.
• W582055897 hasConcept C61272859 @default.
• W582055897 hasConcept C81363708 @default.
• W582055897 hasConcept C95623464 @default.
• W582055897 hasConceptScore W582055897C108583219 @default.
• W582055897 hasConceptScore W582055897C119857082 @default.
• W582055897 hasConceptScore W582055897C138885662 @default.
• W582055897 hasConceptScore W582055897C140331021 @default.
• W582055897 hasConceptScore W582055897C150899416 @default.
• W582055897 hasConceptScore W582055897C153180895 @default.
• W582055897 hasConceptScore W582055897C154945302 @default.
• W582055897 hasConceptScore W582055897C162324750 @default.
• W582055897 hasConceptScore W582055897C165696696 @default.
• W582055897 hasConceptScore W582055897C187736073 @default.
• W582055897 hasConceptScore W582055897C2776401178 @default.
• W582055897 hasConceptScore W582055897C2780451532 @default.
• W582055897 hasConceptScore W582055897C28006648 @default.
• W582055897 hasConceptScore W582055897C2984842247 @default.
• W582055897 hasConceptScore W582055897C38652104 @default.
• W582055897 hasConceptScore W582055897C41008148 @default.
• W582055897 hasConceptScore W582055897C41895202 @default.
• W582055897 hasConceptScore W582055897C50644808 @default.
• W582055897 hasConceptScore W582055897C59404180 @default.
• W582055897 hasConceptScore W582055897C61272859 @default.
• W582055897 hasConceptScore W582055897C81363708 @default.
• W582055897 hasConceptScore W582055897C95623464 @default.

• next