Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891932097> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2891932097 abstract "Annotating a data sample in a multi-label learning problem requires a human oracle to consider the presence/absence of every possible label separately, which is extremely labor intensive. Active learning algorithms automatically identify the informative samples from large amounts of unlabeled data and significantly reduce human annotation efforts in inducing a classification model. Further, deep models have gained popularity to automatically learn representative features from a given dataset and have depicted promising empirical performance in a variety of applications. In this paper, we exploit the feature learning capabilities of deep neural networks and propose a novel framework to address the problem of multi-label active learning with label correlation. We integrate an active selection criterion to the objective function and train deep networks to optimize the function. Our extensive empirical studies on five benchmark multi-label datasets show that our methods outperform the state-of-the-art algorithms, corroborating their potential for real-world image classification applications." @default.
- W2891932097 created "2018-09-27" @default.
- W2891932097 creator A5042050154 @default.
- W2891932097 creator A5066190233 @default.
- W2891932097 creator A5069847440 @default.
- W2891932097 creator A5089498346 @default.
- W2891932097 date "2018-10-01" @default.
- W2891932097 modified "2023-10-02" @default.
- W2891932097 title "Multi-Label Deep Active Learning with Label Correlation" @default.
- W2891932097 cites W1051230991 @default.
- W2891932097 cites W1559923427 @default.
- W2891932097 cites W1753402186 @default.
- W2891932097 cites W1964017540 @default.
- W2891932097 cites W1997069591 @default.
- W2891932097 cites W1997783035 @default.
- W2891932097 cites W2007972815 @default.
- W2891932097 cites W2011674654 @default.
- W2891932097 cites W2017637319 @default.
- W2891932097 cites W2027922120 @default.
- W2891932097 cites W2031489346 @default.
- W2891932097 cites W2052684427 @default.
- W2891932097 cites W2102605133 @default.
- W2891932097 cites W2406223855 @default.
- W2891932097 cites W2483458289 @default.
- W2891932097 cites W2593390164 @default.
- W2891932097 cites W2789833952 @default.
- W2891932097 cites W2919115771 @default.
- W2891932097 cites W2963745697 @default.
- W2891932097 doi "https://doi.org/10.1109/icip.2018.8451460" @default.
- W2891932097 hasPublicationYear "2018" @default.
- W2891932097 type Work @default.
- W2891932097 sameAs 2891932097 @default.
- W2891932097 citedByCount "4" @default.
- W2891932097 countsByYear W28919320972019 @default.
- W2891932097 countsByYear W28919320972020 @default.
- W2891932097 countsByYear W28919320972021 @default.
- W2891932097 countsByYear W28919320972022 @default.
- W2891932097 crossrefType "proceedings-article" @default.
- W2891932097 hasAuthorship W2891932097A5042050154 @default.
- W2891932097 hasAuthorship W2891932097A5066190233 @default.
- W2891932097 hasAuthorship W2891932097A5069847440 @default.
- W2891932097 hasAuthorship W2891932097A5089498346 @default.
- W2891932097 hasConcept C108583219 @default.
- W2891932097 hasConcept C117220453 @default.
- W2891932097 hasConcept C119857082 @default.
- W2891932097 hasConcept C154945302 @default.
- W2891932097 hasConcept C2524010 @default.
- W2891932097 hasConcept C33923547 @default.
- W2891932097 hasConcept C41008148 @default.
- W2891932097 hasConcept C77967617 @default.
- W2891932097 hasConceptScore W2891932097C108583219 @default.
- W2891932097 hasConceptScore W2891932097C117220453 @default.
- W2891932097 hasConceptScore W2891932097C119857082 @default.
- W2891932097 hasConceptScore W2891932097C154945302 @default.
- W2891932097 hasConceptScore W2891932097C2524010 @default.
- W2891932097 hasConceptScore W2891932097C33923547 @default.
- W2891932097 hasConceptScore W2891932097C41008148 @default.
- W2891932097 hasConceptScore W2891932097C77967617 @default.
- W2891932097 hasLocation W28919320971 @default.
- W2891932097 hasOpenAccess W2891932097 @default.
- W2891932097 hasPrimaryLocation W28919320971 @default.
- W2891932097 hasRelatedWork W2597787948 @default.
- W2891932097 hasRelatedWork W2941584439 @default.
- W2891932097 hasRelatedWork W2951786554 @default.
- W2891932097 hasRelatedWork W3040460291 @default.
- W2891932097 hasRelatedWork W3047894882 @default.
- W2891932097 hasRelatedWork W3127985239 @default.
- W2891932097 hasRelatedWork W3168668327 @default.
- W2891932097 hasRelatedWork W3208584567 @default.
- W2891932097 hasRelatedWork W4220895458 @default.
- W2891932097 hasRelatedWork W4225620657 @default.
- W2891932097 isParatext "false" @default.
- W2891932097 isRetracted "false" @default.
- W2891932097 magId "2891932097" @default.
- W2891932097 workType "article" @default.