Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089109701> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3089109701 endingPage "5" @default.
- W3089109701 startingPage "84" @default.
- W3089109701 abstract "This paper presents a new training model for orientation invariant object detection in aerial images by extending a deep learning based RetinaNet which is a single-stage detector based on feature pyramid networks and focal loss for dense object detection. Unlike R3Det which applies feature refinement to handle rotating objects, we proposed further improvement to cope with the densely arranged and class imbalance problems in aerial imaging, on three aspects: 1) All training images are traversed in each iteration instead of only one image in each iteration in order to cover all possibilities; 2) The learning rate is reduced if losses are not reduced; and 3) The learning rate is reduced if losses are not changed. The proposed method was calibrated and validated by comprehensive for performance evaluation and benchmarking. The experiment results demonstrate the significant improvement in comparison with R3Dec approach on the same data set. In addition to the well-known public data set DOTA for benchmarking, a new data set is also established by considering the balance between the training set and testing set. The map of losses which dropped down smoothly without jitter and overfitting also illustrates the advantages of the proposed newmodel." @default.
- W3089109701 created "2020-10-01" @default.
- W3089109701 creator A5009893012 @default.
- W3089109701 creator A5027250401 @default.
- W3089109701 creator A5059310439 @default.
- W3089109701 creator A5065733470 @default.
- W3089109701 creator A5071612326 @default.
- W3089109701 date "2020-01-26" @default.
- W3089109701 modified "2023-09-27" @default.
- W3089109701 title "A New Training Model for Object Detection in Aerial Images" @default.
- W3089109701 doi "https://doi.org/10.2352/issn.2470-1173.2020.8.imawm-084" @default.
- W3089109701 hasPublicationYear "2020" @default.
- W3089109701 type Work @default.
- W3089109701 sameAs 3089109701 @default.
- W3089109701 citedByCount "0" @default.
- W3089109701 crossrefType "journal-article" @default.
- W3089109701 hasAuthorship W3089109701A5009893012 @default.
- W3089109701 hasAuthorship W3089109701A5027250401 @default.
- W3089109701 hasAuthorship W3089109701A5059310439 @default.
- W3089109701 hasAuthorship W3089109701A5065733470 @default.
- W3089109701 hasAuthorship W3089109701A5071612326 @default.
- W3089109701 hasConcept C115961682 @default.
- W3089109701 hasConcept C138885662 @default.
- W3089109701 hasConcept C142575187 @default.
- W3089109701 hasConcept C144133560 @default.
- W3089109701 hasConcept C153180895 @default.
- W3089109701 hasConcept C154945302 @default.
- W3089109701 hasConcept C162853370 @default.
- W3089109701 hasConcept C177264268 @default.
- W3089109701 hasConcept C199360897 @default.
- W3089109701 hasConcept C22019652 @default.
- W3089109701 hasConcept C2524010 @default.
- W3089109701 hasConcept C2776151529 @default.
- W3089109701 hasConcept C2776401178 @default.
- W3089109701 hasConcept C2776429412 @default.
- W3089109701 hasConcept C31972630 @default.
- W3089109701 hasConcept C33923547 @default.
- W3089109701 hasConcept C41008148 @default.
- W3089109701 hasConcept C41895202 @default.
- W3089109701 hasConcept C50644808 @default.
- W3089109701 hasConcept C51632099 @default.
- W3089109701 hasConcept C58489278 @default.
- W3089109701 hasConcept C76155785 @default.
- W3089109701 hasConcept C86251818 @default.
- W3089109701 hasConcept C94915269 @default.
- W3089109701 hasConceptScore W3089109701C115961682 @default.
- W3089109701 hasConceptScore W3089109701C138885662 @default.
- W3089109701 hasConceptScore W3089109701C142575187 @default.
- W3089109701 hasConceptScore W3089109701C144133560 @default.
- W3089109701 hasConceptScore W3089109701C153180895 @default.
- W3089109701 hasConceptScore W3089109701C154945302 @default.
- W3089109701 hasConceptScore W3089109701C162853370 @default.
- W3089109701 hasConceptScore W3089109701C177264268 @default.
- W3089109701 hasConceptScore W3089109701C199360897 @default.
- W3089109701 hasConceptScore W3089109701C22019652 @default.
- W3089109701 hasConceptScore W3089109701C2524010 @default.
- W3089109701 hasConceptScore W3089109701C2776151529 @default.
- W3089109701 hasConceptScore W3089109701C2776401178 @default.
- W3089109701 hasConceptScore W3089109701C2776429412 @default.
- W3089109701 hasConceptScore W3089109701C31972630 @default.
- W3089109701 hasConceptScore W3089109701C33923547 @default.
- W3089109701 hasConceptScore W3089109701C41008148 @default.
- W3089109701 hasConceptScore W3089109701C41895202 @default.
- W3089109701 hasConceptScore W3089109701C50644808 @default.
- W3089109701 hasConceptScore W3089109701C51632099 @default.
- W3089109701 hasConceptScore W3089109701C58489278 @default.
- W3089109701 hasConceptScore W3089109701C76155785 @default.
- W3089109701 hasConceptScore W3089109701C86251818 @default.
- W3089109701 hasConceptScore W3089109701C94915269 @default.
- W3089109701 hasIssue "8" @default.
- W3089109701 hasLocation W30891097011 @default.
- W3089109701 hasOpenAccess W3089109701 @default.
- W3089109701 hasPrimaryLocation W30891097011 @default.
- W3089109701 hasRelatedWork W137416770 @default.
- W3089109701 hasRelatedWork W204046101 @default.
- W3089109701 hasRelatedWork W2090093270 @default.
- W3089109701 hasRelatedWork W2157098127 @default.
- W3089109701 hasRelatedWork W2296151615 @default.
- W3089109701 hasRelatedWork W2534909612 @default.
- W3089109701 hasRelatedWork W2885665929 @default.
- W3089109701 hasRelatedWork W3002270006 @default.
- W3089109701 hasRelatedWork W3005717195 @default.
- W3089109701 hasRelatedWork W3204153416 @default.
- W3089109701 hasVolume "2020" @default.
- W3089109701 isParatext "false" @default.
- W3089109701 isRetracted "false" @default.
- W3089109701 magId "3089109701" @default.
- W3089109701 workType "article" @default.