Matches in SemOpenAlex for { <https://semopenalex.org/work/W2810844163> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2810844163 abstract "In this paper, a deep learning framework is developed to enable path-based tree classifier training for supporting large-scale plant species recognition, where a deep neural network and a tree classifier are jointly trained in an end-to-end fashion. First, a two-layer plant taxonomy is constructed to organize large numbers of plant species and their genus hierarchically in a coarse-to-fine fashion. Second, a deep learning framework is developed to enable path-based tree classifier training, where a tree classifier over the plant taxonomy is used to replace the flat softmax layer in traditional deep CNNs. A path-based error function is defined to optimize the joint process for learning deep CNN and tree classifier, where back propagation is used to update both the classifier parameters and the network weights simultaneously. We have also constructed a large-scale plant database of Orchid family for algorithm evaluation. Our experimental results have demonstrated that our path-based deep learning algorithm can achieve very competitive results on both the accuracy rates and the computational efficiency for large-scale plant species recognition." @default.
- W2810844163 created "2018-07-10" @default.
- W2810844163 creator A5007612908 @default.
- W2810844163 creator A5017775910 @default.
- W2810844163 creator A5024485372 @default.
- W2810844163 creator A5039550464 @default.
- W2810844163 creator A5063145868 @default.
- W2810844163 date "2018-04-01" @default.
- W2810844163 modified "2023-09-27" @default.
- W2810844163 title "Deep Learning of Path-Based Tree Classifiers for Large-Scale Plant Species Identification" @default.
- W2810844163 cites W1970719635 @default.
- W2810844163 cites W1987083125 @default.
- W2810844163 cites W2008835805 @default.
- W2810844163 cites W2014566476 @default.
- W2810844163 cites W2030432742 @default.
- W2810844163 cites W2032317445 @default.
- W2810844163 cites W2039875163 @default.
- W2810844163 cites W2077512673 @default.
- W2810844163 cites W2090950329 @default.
- W2810844163 cites W2097117768 @default.
- W2810844163 cites W2098020658 @default.
- W2810844163 cites W2108598243 @default.
- W2810844163 cites W2110765924 @default.
- W2810844163 cites W2112796928 @default.
- W2810844163 cites W2112993448 @default.
- W2810844163 cites W2116339064 @default.
- W2810844163 cites W2135582619 @default.
- W2810844163 cites W2150856297 @default.
- W2810844163 cites W2438072089 @default.
- W2810844163 cites W2726065210 @default.
- W2810844163 doi "https://doi.org/10.1109/mipr.2018.00013" @default.
- W2810844163 hasPublicationYear "2018" @default.
- W2810844163 type Work @default.
- W2810844163 sameAs 2810844163 @default.
- W2810844163 citedByCount "14" @default.
- W2810844163 countsByYear W28108441632018 @default.
- W2810844163 countsByYear W28108441632019 @default.
- W2810844163 countsByYear W28108441632020 @default.
- W2810844163 countsByYear W28108441632021 @default.
- W2810844163 countsByYear W28108441632022 @default.
- W2810844163 crossrefType "proceedings-article" @default.
- W2810844163 hasAuthorship W2810844163A5007612908 @default.
- W2810844163 hasAuthorship W2810844163A5017775910 @default.
- W2810844163 hasAuthorship W2810844163A5024485372 @default.
- W2810844163 hasAuthorship W2810844163A5039550464 @default.
- W2810844163 hasAuthorship W2810844163A5063145868 @default.
- W2810844163 hasConcept C108583219 @default.
- W2810844163 hasConcept C119857082 @default.
- W2810844163 hasConcept C153180895 @default.
- W2810844163 hasConcept C154945302 @default.
- W2810844163 hasConcept C188441871 @default.
- W2810844163 hasConcept C24412817 @default.
- W2810844163 hasConcept C41008148 @default.
- W2810844163 hasConcept C41806617 @default.
- W2810844163 hasConcept C50644808 @default.
- W2810844163 hasConcept C58642233 @default.
- W2810844163 hasConcept C59822182 @default.
- W2810844163 hasConcept C86803240 @default.
- W2810844163 hasConcept C95623464 @default.
- W2810844163 hasConceptScore W2810844163C108583219 @default.
- W2810844163 hasConceptScore W2810844163C119857082 @default.
- W2810844163 hasConceptScore W2810844163C153180895 @default.
- W2810844163 hasConceptScore W2810844163C154945302 @default.
- W2810844163 hasConceptScore W2810844163C188441871 @default.
- W2810844163 hasConceptScore W2810844163C24412817 @default.
- W2810844163 hasConceptScore W2810844163C41008148 @default.
- W2810844163 hasConceptScore W2810844163C41806617 @default.
- W2810844163 hasConceptScore W2810844163C50644808 @default.
- W2810844163 hasConceptScore W2810844163C58642233 @default.
- W2810844163 hasConceptScore W2810844163C59822182 @default.
- W2810844163 hasConceptScore W2810844163C86803240 @default.
- W2810844163 hasConceptScore W2810844163C95623464 @default.
- W2810844163 hasLocation W28108441631 @default.
- W2810844163 hasOpenAccess W2810844163 @default.
- W2810844163 hasPrimaryLocation W28108441631 @default.
- W2810844163 hasRelatedWork W2743258233 @default.
- W2810844163 hasRelatedWork W2771515600 @default.
- W2810844163 hasRelatedWork W2807311372 @default.
- W2810844163 hasRelatedWork W2971416272 @default.
- W2810844163 hasRelatedWork W3023402959 @default.
- W2810844163 hasRelatedWork W3158264953 @default.
- W2810844163 hasRelatedWork W4221015625 @default.
- W2810844163 hasRelatedWork W4307834408 @default.
- W2810844163 hasRelatedWork W4323060069 @default.
- W2810844163 hasRelatedWork W564581980 @default.
- W2810844163 isParatext "false" @default.
- W2810844163 isRetracted "false" @default.
- W2810844163 magId "2810844163" @default.
- W2810844163 workType "article" @default.