FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205691925> ?p ?o ?g. }

• W4205691925 endingPage "607" @default.
• W4205691925 startingPage "593" @default.
• W4205691925 abstract "We describe a novel semi-supervised learning method that reduces the labelling effort needed to train convolutional neural networks (CNNs) when processing georeferenced imagery. This allows deep learning CNNs to be trained on a per-dataset basis, which is useful in domains where there is limited learning transferability across datasets. The method identifies representative subsets of images from an unlabelled dataset based on the latent representation of a location guided autoencoder. We assess the method's sensitivities to design options using four different ground-truthed datasets of georeferenced environmental monitoring images, where these include various scenes in aerial and seafloor imagery. Efficiency gains are achieved for all the aerial and seafloor image datasets analysed in our experiments, demonstrating the benefit of the method across application domains. Compared to CNNs of the same architecture trained using conventional transfer and active learning, the method achieves equivalent accuracy with an order of magnitude fewer annotations, and 85 % of the accuracy of CNNs trained conventionally with approximately 10,000 human annotations using just 40 prioritised annotations. The biggest gains in efficiency are seen in datasets with unbalanced class distributions and rare classes that have a relatively small number of observations." @default.
• W4205691925 created "2022-01-26" @default.
• W4205691925 creator A5001921709 @default.
• W4205691925 creator A5035668901 @default.
• W4205691925 creator A5039161868 @default.
• W4205691925 creator A5044131792 @default.
• W4205691925 creator A5046941095 @default.
• W4205691925 creator A5068908958 @default.
• W4205691925 date "2023-01-01" @default.
• W4205691925 modified "2023-10-18" @default.
• W4205691925 title "Guiding Labelling Effort for Efficient Learning With Georeferenced Images" @default.
• W4205691925 cites W1522156302 @default.
• W4205691925 cites W1861492603 @default.
• W4205691925 cites W1936223240 @default.
• W4205691925 cites W1961501874 @default.
• W4205691925 cites W1992396639 @default.
• W4205691925 cites W1998943389 @default.
• W4205691925 cites W2001123951 @default.
• W4205691925 cites W2037227137 @default.
• W4205691925 cites W2076131212 @default.
• W4205691925 cites W2108598243 @default.
• W4205691925 cites W2115579991 @default.
• W4205691925 cites W2118941120 @default.
• W4205691925 cites W2128017662 @default.
• W4205691925 cites W2140792329 @default.
• W4205691925 cites W2163352848 @default.
• W4205691925 cites W2169827072 @default.
• W4205691925 cites W2194775991 @default.
• W4205691925 cites W2248723555 @default.
• W4205691925 cites W2253429366 @default.
• W4205691925 cites W2342880667 @default.
• W4205691925 cites W2510508657 @default.
• W4205691925 cites W2512351403 @default.
• W4205691925 cites W2516076665 @default.
• W4205691925 cites W2523983814 @default.
• W4205691925 cites W2548094124 @default.
• W4205691925 cites W2576300543 @default.
• W4205691925 cites W2597876337 @default.
• W4205691925 cites W2750023899 @default.
• W4205691925 cites W2768975974 @default.
• W4205691925 cites W2783353659 @default.
• W4205691925 cites W2887280559 @default.
• W4205691925 cites W2900751312 @default.
• W4205691925 cites W2905035870 @default.
• W4205691925 cites W2940726923 @default.
• W4205691925 cites W2954996726 @default.
• W4205691925 cites W2955950606 @default.
• W4205691925 cites W2964246847 @default.
• W4205691925 cites W2979805229 @default.
• W4205691925 cites W3016453764 @default.
• W4205691925 cites W3024543081 @default.
• W4205691925 cites W3031943955 @default.
• W4205691925 cites W3041943617 @default.
• W4205691925 cites W3047626901 @default.
• W4205691925 cites W3091002423 @default.
• W4205691925 cites W3091528367 @default.
• W4205691925 cites W81068503 @default.
• W4205691925 cites W946771493 @default.
• W4205691925 cites W2146715576 @default.
• W4205691925 doi "https://doi.org/10.1109/tpami.2021.3140060" @default.
• W4205691925 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34982674" @default.
• W4205691925 hasPublicationYear "2023" @default.
• W4205691925 type Work @default.
• W4205691925 citedByCount "1" @default.
• W4205691925 countsByYear W42056919252022 @default.
• W4205691925 crossrefType "journal-article" @default.
• W4205691925 hasAuthorship W4205691925A5001921709 @default.
• W4205691925 hasAuthorship W4205691925A5035668901 @default.
• W4205691925 hasAuthorship W4205691925A5039161868 @default.
• W4205691925 hasAuthorship W4205691925A5044131792 @default.
• W4205691925 hasAuthorship W4205691925A5046941095 @default.
• W4205691925 hasAuthorship W4205691925A5068908958 @default.
• W4205691925 hasBestOaLocation W42056919251 @default.
• W4205691925 hasConcept C101738243 @default.
• W4205691925 hasConcept C108583219 @default.
• W4205691925 hasConcept C119857082 @default.
• W4205691925 hasConcept C140331021 @default.
• W4205691925 hasConcept C150899416 @default.
• W4205691925 hasConcept C153180895 @default.
• W4205691925 hasConcept C154945302 @default.
• W4205691925 hasConcept C41008148 @default.
• W4205691925 hasConcept C61272859 @default.
• W4205691925 hasConcept C81363708 @default.
• W4205691925 hasConceptScore W4205691925C101738243 @default.
• W4205691925 hasConceptScore W4205691925C108583219 @default.
• W4205691925 hasConceptScore W4205691925C119857082 @default.
• W4205691925 hasConceptScore W4205691925C140331021 @default.
• W4205691925 hasConceptScore W4205691925C150899416 @default.
• W4205691925 hasConceptScore W4205691925C153180895 @default.
• W4205691925 hasConceptScore W4205691925C154945302 @default.
• W4205691925 hasConceptScore W4205691925C41008148 @default.
• W4205691925 hasConceptScore W4205691925C61272859 @default.
• W4205691925 hasConceptScore W4205691925C81363708 @default.
• W4205691925 hasFunder F4320334631 @default.
• W4205691925 hasFunder F4320334704 @default.
• W4205691925 hasIssue "1" @default.
• W4205691925 hasLocation W42056919251 @default.
• W4205691925 hasLocation W42056919252 @default.

• next