FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2944173897> ?p ?o ?g. }

• W2944173897 abstract "The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as uncertain. A variety of recent methods have been proposed to apply active learning to deep networks but most of them are either designed specific for their target tasks or computationally inefficient for large networks. In this paper, we propose a novel active learning method that is simple but task-agnostic, and works efficiently with the deep networks. We attach a small parametric named prediction module, to a target network, and learn it to predict target losses of unlabeled inputs. Then, this module can suggest data that the target model is likely to produce a wrong prediction. This method is task-agnostic as networks are learned from a single loss regardless of target tasks. We rigorously validate our method through image classification, object detection, and human pose estimation, with the recent network architectures. The results demonstrate that our method consistently outperforms the previous methods over the tasks." @default.
• W2944173897 created "2019-05-16" @default.
• W2944173897 creator A5012455275 @default.
• W2944173897 creator A5063965796 @default.
• W2944173897 date "2019-05-09" @default.
• W2944173897 modified "2023-09-23" @default.
• W2944173897 title "Learning Loss for Active Learning" @default.
• W2944173897 cites W1513874326 @default.
• W2944173897 cites W1514707997 @default.
• W2944173897 cites W1520997877 @default.
• W2944173897 cites W1551841473 @default.
• W2944173897 cites W1589990798 @default.
• W2944173897 cites W1686810756 @default.
• W2944173897 cites W2008989859 @default.
• W2944173897 cites W2026566343 @default.
• W2944173897 cites W2031489346 @default.
• W2944173897 cites W2034747098 @default.
• W2944173897 cites W2080021732 @default.
• W2944173897 cites W2080873731 @default.
• W2944173897 cites W2085989833 @default.
• W2944173897 cites W2119720396 @default.
• W2944173897 cites W2124244761 @default.
• W2944173897 cites W2128678390 @default.
• W2944173897 cites W2132948751 @default.
• W2944173897 cites W2140535827 @default.
• W2944173897 cites W2163605009 @default.
• W2944173897 cites W2167828456 @default.
• W2944173897 cites W2168356304 @default.
• W2944173897 cites W2171671120 @default.
• W2944173897 cites W2194775991 @default.
• W2944173897 cites W2221898772 @default.
• W2944173897 cites W2233838193 @default.
• W2944173897 cites W2262342046 @default.
• W2944173897 cites W2287655724 @default.
• W2944173897 cites W2307770531 @default.
• W2944173897 cites W2426031434 @default.
• W2944173897 cites W2460470859 @default.
• W2944173897 cites W2558661413 @default.
• W2944173897 cites W2575032143 @default.
• W2944173897 cites W2581852757 @default.
• W2944173897 cites W2585292948 @default.
• W2944173897 cites W2597787948 @default.
• W2944173897 cites W2625559849 @default.
• W2944173897 cites W2747178704 @default.
• W2944173897 cites W2750023899 @default.
• W2944173897 cites W2750549109 @default.
• W2944173897 cites W2777262900 @default.
• W2944173897 cites W2798820905 @default.
• W2944173897 cites W2899771611 @default.
• W2944173897 cites W2914331073 @default.
• W2944173897 cites W2962819936 @default.
• W2944173897 cites W2963296620 @default.
• W2944173897 cites W2963703197 @default.
• W2944173897 cites W2963902936 @default.
• W2944173897 cites W2964059111 @default.
• W2944173897 cites W3118608800 @default.
• W2944173897 cites W343636949 @default.
• W2944173897 cites W71169749 @default.
• W2944173897 cites W830076066 @default.
• W2944173897 cites W2998213596 @default.
• W2944173897 hasPublicationYear "2019" @default.
• W2944173897 type Work @default.
• W2944173897 sameAs 2944173897 @default.
• W2944173897 citedByCount "6" @default.
• W2944173897 countsByYear W29441738972019 @default.
• W2944173897 countsByYear W29441738972020 @default.
• W2944173897 countsByYear W29441738972021 @default.
• W2944173897 crossrefType "posted-content" @default.
• W2944173897 hasAuthorship W2944173897A5012455275 @default.
• W2944173897 hasAuthorship W2944173897A5063965796 @default.
• W2944173897 hasConcept C105795698 @default.
• W2944173897 hasConcept C108583219 @default.
• W2944173897 hasConcept C111472728 @default.
• W2944173897 hasConcept C117251300 @default.
• W2944173897 hasConcept C119857082 @default.
• W2944173897 hasConcept C136197465 @default.
• W2944173897 hasConcept C138885662 @default.
• W2944173897 hasConcept C154945302 @default.
• W2944173897 hasConcept C162324750 @default.
• W2944173897 hasConcept C187736073 @default.
• W2944173897 hasConcept C2776321320 @default.
• W2944173897 hasConcept C2780451532 @default.
• W2944173897 hasConcept C2780586882 @default.
• W2944173897 hasConcept C2781238097 @default.
• W2944173897 hasConcept C2984842247 @default.
• W2944173897 hasConcept C33923547 @default.
• W2944173897 hasConcept C41008148 @default.
• W2944173897 hasConcept C50644808 @default.
• W2944173897 hasConcept C77967617 @default.
• W2944173897 hasConceptScore W2944173897C105795698 @default.
• W2944173897 hasConceptScore W2944173897C108583219 @default.
• W2944173897 hasConceptScore W2944173897C111472728 @default.
• W2944173897 hasConceptScore W2944173897C117251300 @default.
• W2944173897 hasConceptScore W2944173897C119857082 @default.
• W2944173897 hasConceptScore W2944173897C136197465 @default.
• W2944173897 hasConceptScore W2944173897C138885662 @default.
• W2944173897 hasConceptScore W2944173897C154945302 @default.
• W2944173897 hasConceptScore W2944173897C162324750 @default.
• W2944173897 hasConceptScore W2944173897C187736073 @default.
• W2944173897 hasConceptScore W2944173897C2776321320 @default.

• next