Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313201808> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313201808 endingPage "103159" @default.
- W4313201808 startingPage "103159" @default.
- W4313201808 abstract "Road extraction from remote sensing imagery is a fundamental task in the field of image semantic segmentation. For this goal, numerous supervised deep learning techniques have been created, along with the employment of various loss functions that play a crucial role in determining the performances of supervised learning models. However, there is a lack of comprehensive analysis of the performance differences between the loss functions for road segmentation in remote sensing imagery. Therefore, this study conducts a comparative study of 12 well-known loss functions used widely in the field of image segmentation by training and evaluating the representative D-LinkNet network for road segmentation tasks with two publicly available remote sensing road datasets consisting of very high-resolution aerial and satellite images. The results show that different loss functions could lead to very different outcomes using the D-LinkNet, with varying focuses such as on overall model performances, precision, or recall. By dividing the loss functions into the distribution-based, region-based, and compound ones, we found that the region-based loss function type led to generally better model performances than the distribution-based one in terms of F1, IoU, and the road segmentation maps, with the compound loss function type being comparable to the region-based one. This paper eventually tries to offer suggestions for choosing the loss function that best suits the purposes of road segmentation-related studies." @default.
- W4313201808 created "2023-01-06" @default.
- W4313201808 creator A5007144110 @default.
- W4313201808 creator A5017266329 @default.
- W4313201808 creator A5032270954 @default.
- W4313201808 creator A5042973046 @default.
- W4313201808 creator A5049403375 @default.
- W4313201808 date "2023-02-01" @default.
- W4313201808 modified "2023-09-26" @default.
- W4313201808 title "A comparative study of loss functions for road segmentation in remotely sensed road datasets" @default.
- W4313201808 cites W1909740415 @default.
- W4313201808 cites W2029377763 @default.
- W4313201808 cites W2114268578 @default.
- W4313201808 cites W2607333215 @default.
- W4313201808 cites W2774320778 @default.
- W4313201808 cites W2884561390 @default.
- W4313201808 cites W2898504016 @default.
- W4313201808 cites W2963043051 @default.
- W4313201808 cites W2963400045 @default.
- W4313201808 cites W2963881378 @default.
- W4313201808 cites W2964309882 @default.
- W4313201808 cites W2966866040 @default.
- W4313201808 cites W3021297918 @default.
- W4313201808 cites W3033237758 @default.
- W4313201808 cites W3086017879 @default.
- W4313201808 cites W3103263155 @default.
- W4313201808 cites W3111683216 @default.
- W4313201808 cites W3136424010 @default.
- W4313201808 cites W4200512530 @default.
- W4313201808 cites W4205100051 @default.
- W4313201808 cites W4220717988 @default.
- W4313201808 cites W4224256039 @default.
- W4313201808 cites W4308300881 @default.
- W4313201808 doi "https://doi.org/10.1016/j.jag.2022.103159" @default.
- W4313201808 hasPublicationYear "2023" @default.
- W4313201808 type Work @default.
- W4313201808 citedByCount "1" @default.
- W4313201808 countsByYear W43132018082023 @default.
- W4313201808 crossrefType "journal-article" @default.
- W4313201808 hasAuthorship W4313201808A5007144110 @default.
- W4313201808 hasAuthorship W4313201808A5017266329 @default.
- W4313201808 hasAuthorship W4313201808A5032270954 @default.
- W4313201808 hasAuthorship W4313201808A5042973046 @default.
- W4313201808 hasAuthorship W4313201808A5049403375 @default.
- W4313201808 hasBestOaLocation W43132018081 @default.
- W4313201808 hasConcept C108583219 @default.
- W4313201808 hasConcept C124101348 @default.
- W4313201808 hasConcept C124504099 @default.
- W4313201808 hasConcept C14036430 @default.
- W4313201808 hasConcept C154945302 @default.
- W4313201808 hasConcept C202444582 @default.
- W4313201808 hasConcept C205649164 @default.
- W4313201808 hasConcept C2778102629 @default.
- W4313201808 hasConcept C31972630 @default.
- W4313201808 hasConcept C33923547 @default.
- W4313201808 hasConcept C41008148 @default.
- W4313201808 hasConcept C62649853 @default.
- W4313201808 hasConcept C78458016 @default.
- W4313201808 hasConcept C86803240 @default.
- W4313201808 hasConcept C89600930 @default.
- W4313201808 hasConcept C9652623 @default.
- W4313201808 hasConceptScore W4313201808C108583219 @default.
- W4313201808 hasConceptScore W4313201808C124101348 @default.
- W4313201808 hasConceptScore W4313201808C124504099 @default.
- W4313201808 hasConceptScore W4313201808C14036430 @default.
- W4313201808 hasConceptScore W4313201808C154945302 @default.
- W4313201808 hasConceptScore W4313201808C202444582 @default.
- W4313201808 hasConceptScore W4313201808C205649164 @default.
- W4313201808 hasConceptScore W4313201808C2778102629 @default.
- W4313201808 hasConceptScore W4313201808C31972630 @default.
- W4313201808 hasConceptScore W4313201808C33923547 @default.
- W4313201808 hasConceptScore W4313201808C41008148 @default.
- W4313201808 hasConceptScore W4313201808C62649853 @default.
- W4313201808 hasConceptScore W4313201808C78458016 @default.
- W4313201808 hasConceptScore W4313201808C86803240 @default.
- W4313201808 hasConceptScore W4313201808C89600930 @default.
- W4313201808 hasConceptScore W4313201808C9652623 @default.
- W4313201808 hasLocation W43132018081 @default.
- W4313201808 hasOpenAccess W4313201808 @default.
- W4313201808 hasPrimaryLocation W43132018081 @default.
- W4313201808 hasRelatedWork W1669643531 @default.
- W4313201808 hasRelatedWork W1982826852 @default.
- W4313201808 hasRelatedWork W2005437358 @default.
- W4313201808 hasRelatedWork W2008656436 @default.
- W4313201808 hasRelatedWork W2023558673 @default.
- W4313201808 hasRelatedWork W2110230079 @default.
- W4313201808 hasRelatedWork W2134924024 @default.
- W4313201808 hasRelatedWork W2517104666 @default.
- W4313201808 hasRelatedWork W2790662084 @default.
- W4313201808 hasRelatedWork W4285827401 @default.
- W4313201808 hasVolume "116" @default.
- W4313201808 isParatext "false" @default.
- W4313201808 isRetracted "false" @default.
- W4313201808 workType "article" @default.