FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285220488> ?p ?o ?g. }

• W4285220488 endingPage "46" @default.
• W4285220488 startingPage "34" @default.
• W4285220488 abstract "We apply deep metric learning for the first time to the problem of classifying planktic foraminifer shells on microscopic images. This species recognition task is an important information source and scientific pillar for reconstructing past climates. All foraminifer CNN recognition pipelines in the literature produce black-box classifiers that lack visualisation options for human experts and cannot be applied to open set problems. Here, we benchmark metric learning against these pipelines, produce the first scientific visualisation of the phenotypic planktic foraminifer morphology space, and demonstrate that metric learning can be used to cluster species unseen during training. We show that metric learning outperforms all published CNN-based state-of-the-art benchmarks in this domain. We evaluate our approach on the 34,640 expert-annotated images of the Endless Forams public library of 35 modern planktic foramini-fera species. Our results on this data show leading $$92%$$ accuracy (at 0.84 F1-score) in reproducing expert labels on withheld test data, and $$66.5%$$ accuracy (at 0.70 F1-score) when clustering species never encountered in training. We conclude that metric learning is highly effective for this domain and serves as an important tool towards expert-in-the-loop automation of microfossil identification. Key code, network weights, and data splits are published with this paper for full reproducibility." @default.
• W4285220488 created "2022-07-14" @default.
• W4285220488 creator A5001964785 @default.
• W4285220488 creator A5010232055 @default.
• W4285220488 creator A5052504255 @default.
• W4285220488 creator A5058668673 @default.
• W4285220488 creator A5076394448 @default.
• W4285220488 date "2022-01-01" @default.
• W4285220488 modified "2023-10-16" @default.
• W4285220488 title "Visual Microfossil Identification via Deep Metric Learning" @default.
• W4285220488 cites W1539190280 @default.
• W4285220488 cites W1859465057 @default.
• W4285220488 cites W1935868227 @default.
• W4285220488 cites W1966092192 @default.
• W4285220488 cites W1991510654 @default.
• W4285220488 cites W1998871699 @default.
• W4285220488 cites W2006006524 @default.
• W4285220488 cites W2015484390 @default.
• W4285220488 cites W2017488699 @default.
• W4285220488 cites W2019477460 @default.
• W4285220488 cites W2029323798 @default.
• W4285220488 cites W2032593695 @default.
• W4285220488 cites W2051437470 @default.
• W4285220488 cites W2097117768 @default.
• W4285220488 cites W2099855577 @default.
• W4285220488 cites W2100761409 @default.
• W4285220488 cites W2116988018 @default.
• W4285220488 cites W2120590985 @default.
• W4285220488 cites W2156212706 @default.
• W4285220488 cites W2194775991 @default.
• W4285220488 cites W2549139847 @default.
• W4285220488 cites W2567391022 @default.
• W4285220488 cites W2580726517 @default.
• W4285220488 cites W2889471070 @default.
• W4285220488 cites W2897345725 @default.
• W4285220488 cites W2902142885 @default.
• W4285220488 cites W2911528471 @default.
• W4285220488 cites W2922281845 @default.
• W4285220488 cites W2949889661 @default.
• W4285220488 cites W2994127003 @default.
• W4285220488 cites W3035522863 @default.
• W4285220488 cites W3093320302 @default.
• W4285220488 cites W4239510810 @default.
• W4285220488 cites W4285220488 @default.
• W4285220488 cites W4300141286 @default.
• W4285220488 cites W4300672471 @default.
• W4285220488 doi "https://doi.org/10.1007/978-3-031-09037-0_4" @default.
• W4285220488 hasPublicationYear "2022" @default.
• W4285220488 type Work @default.
• W4285220488 citedByCount "5" @default.
• W4285220488 countsByYear W42852204882022 @default.
• W4285220488 countsByYear W42852204882023 @default.
• W4285220488 crossrefType "book-chapter" @default.
• W4285220488 hasAuthorship W4285220488A5001964785 @default.
• W4285220488 hasAuthorship W4285220488A5010232055 @default.
• W4285220488 hasAuthorship W4285220488A5052504255 @default.
• W4285220488 hasAuthorship W4285220488A5058668673 @default.
• W4285220488 hasAuthorship W4285220488A5076394448 @default.
• W4285220488 hasBestOaLocation W42852204882 @default.
• W4285220488 hasConcept C103278499 @default.
• W4285220488 hasConcept C108583219 @default.
• W4285220488 hasConcept C115961682 @default.
• W4285220488 hasConcept C116834253 @default.
• W4285220488 hasConcept C119857082 @default.
• W4285220488 hasConcept C13280743 @default.
• W4285220488 hasConcept C134306372 @default.
• W4285220488 hasConcept C153180895 @default.
• W4285220488 hasConcept C154945302 @default.
• W4285220488 hasConcept C162324750 @default.
• W4285220488 hasConcept C176217482 @default.
• W4285220488 hasConcept C185798385 @default.
• W4285220488 hasConcept C205649164 @default.
• W4285220488 hasConcept C21547014 @default.
• W4285220488 hasConcept C33923547 @default.
• W4285220488 hasConcept C36464697 @default.
• W4285220488 hasConcept C36503486 @default.
• W4285220488 hasConcept C41008148 @default.
• W4285220488 hasConcept C59822182 @default.
• W4285220488 hasConcept C73555534 @default.
• W4285220488 hasConcept C86803240 @default.
• W4285220488 hasConceptScore W4285220488C103278499 @default.
• W4285220488 hasConceptScore W4285220488C108583219 @default.
• W4285220488 hasConceptScore W4285220488C115961682 @default.
• W4285220488 hasConceptScore W4285220488C116834253 @default.
• W4285220488 hasConceptScore W4285220488C119857082 @default.
• W4285220488 hasConceptScore W4285220488C13280743 @default.
• W4285220488 hasConceptScore W4285220488C134306372 @default.
• W4285220488 hasConceptScore W4285220488C153180895 @default.
• W4285220488 hasConceptScore W4285220488C154945302 @default.
• W4285220488 hasConceptScore W4285220488C162324750 @default.
• W4285220488 hasConceptScore W4285220488C176217482 @default.
• W4285220488 hasConceptScore W4285220488C185798385 @default.
• W4285220488 hasConceptScore W4285220488C205649164 @default.
• W4285220488 hasConceptScore W4285220488C21547014 @default.
• W4285220488 hasConceptScore W4285220488C33923547 @default.
• W4285220488 hasConceptScore W4285220488C36464697 @default.
• W4285220488 hasConceptScore W4285220488C36503486 @default.
• W4285220488 hasConceptScore W4285220488C41008148 @default.

• next