Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387332510> ?p ?o ?g. }
- W4387332510 endingPage "469" @default.
- W4387332510 startingPage "469" @default.
- W4387332510 abstract "We present a novel approach to providing greater insight into the characteristics of an unlabelled dataset, increasing the efficiency with which labelled datasets can be created. We leverage dimension-reduction techniques in combination with autoencoders to create an efficient feature representation for image tiles derived from remote sensing satellite imagery. The proposed methodology consists of two main stages. Firstly, an autoencoder network is utilised to reduce the high-dimensional image tile data into a compact and expressive latentfeature representation. Subsequently, features are further reduced to a two-dimensional embedding space using the manifold learning algorithm Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbour Embedding (t-SNE). This step enables the visualization of the image tile clusters in a 2D plot, providing an intuitive and interactive representation that can be used to aid rapid and geographically distributed image labelling. To facilitate the labelling process, our approach allows users to interact with the 2D visualization and label clusters based on their domain knowledge. In cases where certain classes are not effectively separated, users can re-apply dimension reduction to interactively refine subsets of clusters and achieve better class separation, enabling a comprehensively labelled dataset. We evaluate the proposed approach on real-world remote sensing satellite image datasets and demonstrate its effectiveness in achieving accurate and efficient image tile clustering and labelling. Users actively participate in the labelling process through our interactive approach, leading to enhanced relevance of the labelled data, by allowing domain experts to contribute their expertise and enrich the dataset for improved downstream analysis and applications." @default.
- W4387332510 created "2023-10-05" @default.
- W4387332510 creator A5012058010 @default.
- W4387332510 creator A5028781666 @default.
- W4387332510 creator A5042523801 @default.
- W4387332510 date "2023-10-04" @default.
- W4387332510 modified "2023-10-14" @default.
- W4387332510 title "Manifold Explorer: Satellite Image Labelling and Clustering Tool with Using Deep Convolutional Autoencoders" @default.
- W4387332510 cites W1991207049 @default.
- W4387332510 cites W2001141328 @default.
- W4387332510 cites W2015755066 @default.
- W4387332510 cites W2047334881 @default.
- W4387332510 cites W2063907334 @default.
- W4387332510 cites W2077509829 @default.
- W4387332510 cites W2095483845 @default.
- W4387332510 cites W2101678239 @default.
- W4387332510 cites W2117106867 @default.
- W4387332510 cites W2144999986 @default.
- W4387332510 cites W2219715551 @default.
- W4387332510 cites W2255388164 @default.
- W4387332510 cites W2401246392 @default.
- W4387332510 cites W2491477437 @default.
- W4387332510 cites W2886702754 @default.
- W4387332510 cites W2936517889 @default.
- W4387332510 cites W2940726923 @default.
- W4387332510 cites W2944544072 @default.
- W4387332510 cites W2981537605 @default.
- W4387332510 cites W2995664936 @default.
- W4387332510 cites W3017092406 @default.
- W4387332510 cites W3017628311 @default.
- W4387332510 cites W3093905312 @default.
- W4387332510 cites W3111930483 @default.
- W4387332510 cites W3123291413 @default.
- W4387332510 cites W3127452014 @default.
- W4387332510 cites W3131860561 @default.
- W4387332510 cites W3200490011 @default.
- W4387332510 cites W3207667596 @default.
- W4387332510 cites W3217746002 @default.
- W4387332510 cites W4246354968 @default.
- W4387332510 cites W4280592903 @default.
- W4387332510 doi "https://doi.org/10.3390/a16100469" @default.
- W4387332510 hasPublicationYear "2023" @default.
- W4387332510 type Work @default.
- W4387332510 citedByCount "0" @default.
- W4387332510 crossrefType "journal-article" @default.
- W4387332510 hasAuthorship W4387332510A5012058010 @default.
- W4387332510 hasAuthorship W4387332510A5028781666 @default.
- W4387332510 hasAuthorship W4387332510A5042523801 @default.
- W4387332510 hasBestOaLocation W43873325101 @default.
- W4387332510 hasConcept C101738243 @default.
- W4387332510 hasConcept C108583219 @default.
- W4387332510 hasConcept C153083717 @default.
- W4387332510 hasConcept C153180895 @default.
- W4387332510 hasConcept C154945302 @default.
- W4387332510 hasConcept C17744445 @default.
- W4387332510 hasConcept C199539241 @default.
- W4387332510 hasConcept C2776359362 @default.
- W4387332510 hasConcept C36464697 @default.
- W4387332510 hasConcept C41008148 @default.
- W4387332510 hasConcept C41608201 @default.
- W4387332510 hasConcept C59404180 @default.
- W4387332510 hasConcept C70518039 @default.
- W4387332510 hasConcept C73555534 @default.
- W4387332510 hasConcept C81363708 @default.
- W4387332510 hasConcept C94625758 @default.
- W4387332510 hasConceptScore W4387332510C101738243 @default.
- W4387332510 hasConceptScore W4387332510C108583219 @default.
- W4387332510 hasConceptScore W4387332510C153083717 @default.
- W4387332510 hasConceptScore W4387332510C153180895 @default.
- W4387332510 hasConceptScore W4387332510C154945302 @default.
- W4387332510 hasConceptScore W4387332510C17744445 @default.
- W4387332510 hasConceptScore W4387332510C199539241 @default.
- W4387332510 hasConceptScore W4387332510C2776359362 @default.
- W4387332510 hasConceptScore W4387332510C36464697 @default.
- W4387332510 hasConceptScore W4387332510C41008148 @default.
- W4387332510 hasConceptScore W4387332510C41608201 @default.
- W4387332510 hasConceptScore W4387332510C59404180 @default.
- W4387332510 hasConceptScore W4387332510C70518039 @default.
- W4387332510 hasConceptScore W4387332510C73555534 @default.
- W4387332510 hasConceptScore W4387332510C81363708 @default.
- W4387332510 hasConceptScore W4387332510C94625758 @default.
- W4387332510 hasFunder F4320334627 @default.
- W4387332510 hasIssue "10" @default.
- W4387332510 hasLocation W43873325101 @default.
- W4387332510 hasOpenAccess W4387332510 @default.
- W4387332510 hasPrimaryLocation W43873325101 @default.
- W4387332510 hasRelatedWork W2335364074 @default.
- W4387332510 hasRelatedWork W2592385986 @default.
- W4387332510 hasRelatedWork W2772780115 @default.
- W4387332510 hasRelatedWork W2784313445 @default.
- W4387332510 hasRelatedWork W2912933387 @default.
- W4387332510 hasRelatedWork W2998168123 @default.
- W4387332510 hasRelatedWork W3165463024 @default.
- W4387332510 hasRelatedWork W4287178339 @default.
- W4387332510 hasRelatedWork W4287995534 @default.
- W4387332510 hasRelatedWork W4300480195 @default.
- W4387332510 hasVolume "16" @default.
- W4387332510 isParatext "false" @default.