Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901571414> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2901571414 abstract "Recently, convolutional neural networks (CNNs) have received substantial attention in the literature for object recognition (e.g., buildings and roads) in several remote sensing data modalities (e.g., aerial color imagery). Although CNNs have exhibited excellent recognition performance, recent research suggests that trained CNNs can often perform very poorly when applied to data collected over new geographic regions, and for which little labeled training data is available. In this work, we consider the adversarial discriminative domain adaptation (ADDA) approach to address this limitation, due its recent success on related problems. A limitation of ADDA is that it is unsupervised, so in this work we extend ADDA to a semi-supervised algorithm, in which we assume that both labeled and unlabeled data are available in the new domain (e.g., in new geographic region to be evaluated). We compare semi-supervised ADDA to ADDA and a standard fine-tuning approach wherein available labeled data is used for standard CNN training. We perform experiments on two remote sensing datasets and the results indicate that semi-supervised ADDA consistently improves over the other approaches when small amounts of labeled training data are available in the new domain." @default.
- W2901571414 created "2018-11-29" @default.
- W2901571414 creator A5004578492 @default.
- W2901571414 creator A5007239332 @default.
- W2901571414 creator A5054438743 @default.
- W2901571414 creator A5070812231 @default.
- W2901571414 date "2018-07-01" @default.
- W2901571414 modified "2023-09-27" @default.
- W2901571414 title "Semisupervised Adversarial Discriminative Domain Adaptation, with Applicationto Remote Sensing Data" @default.
- W2901571414 cites W1686810756 @default.
- W2901571414 cites W2107298017 @default.
- W2901571414 cites W2575615142 @default.
- W2901571414 cites W2593768305 @default.
- W2901571414 cites W2782522152 @default.
- W2901571414 cites W2890818786 @default.
- W2901571414 cites W2949212125 @default.
- W2901571414 cites W2963275094 @default.
- W2901571414 cites W2964121744 @default.
- W2901571414 doi "https://doi.org/10.1109/igarss.2018.8518096" @default.
- W2901571414 hasPublicationYear "2018" @default.
- W2901571414 type Work @default.
- W2901571414 sameAs 2901571414 @default.
- W2901571414 citedByCount "1" @default.
- W2901571414 countsByYear W29015714142021 @default.
- W2901571414 crossrefType "proceedings-article" @default.
- W2901571414 hasAuthorship W2901571414A5004578492 @default.
- W2901571414 hasAuthorship W2901571414A5007239332 @default.
- W2901571414 hasAuthorship W2901571414A5054438743 @default.
- W2901571414 hasAuthorship W2901571414A5070812231 @default.
- W2901571414 hasConcept C119857082 @default.
- W2901571414 hasConcept C120665830 @default.
- W2901571414 hasConcept C121332964 @default.
- W2901571414 hasConcept C134306372 @default.
- W2901571414 hasConcept C139807058 @default.
- W2901571414 hasConcept C153180895 @default.
- W2901571414 hasConcept C154945302 @default.
- W2901571414 hasConcept C2776145971 @default.
- W2901571414 hasConcept C2776151529 @default.
- W2901571414 hasConcept C2776434776 @default.
- W2901571414 hasConcept C33923547 @default.
- W2901571414 hasConcept C36503486 @default.
- W2901571414 hasConcept C41008148 @default.
- W2901571414 hasConcept C81363708 @default.
- W2901571414 hasConcept C95623464 @default.
- W2901571414 hasConcept C97931131 @default.
- W2901571414 hasConceptScore W2901571414C119857082 @default.
- W2901571414 hasConceptScore W2901571414C120665830 @default.
- W2901571414 hasConceptScore W2901571414C121332964 @default.
- W2901571414 hasConceptScore W2901571414C134306372 @default.
- W2901571414 hasConceptScore W2901571414C139807058 @default.
- W2901571414 hasConceptScore W2901571414C153180895 @default.
- W2901571414 hasConceptScore W2901571414C154945302 @default.
- W2901571414 hasConceptScore W2901571414C2776145971 @default.
- W2901571414 hasConceptScore W2901571414C2776151529 @default.
- W2901571414 hasConceptScore W2901571414C2776434776 @default.
- W2901571414 hasConceptScore W2901571414C33923547 @default.
- W2901571414 hasConceptScore W2901571414C36503486 @default.
- W2901571414 hasConceptScore W2901571414C41008148 @default.
- W2901571414 hasConceptScore W2901571414C81363708 @default.
- W2901571414 hasConceptScore W2901571414C95623464 @default.
- W2901571414 hasConceptScore W2901571414C97931131 @default.
- W2901571414 hasLocation W29015714141 @default.
- W2901571414 hasOpenAccess W2901571414 @default.
- W2901571414 hasPrimaryLocation W29015714141 @default.
- W2901571414 hasRelatedWork W2024160000 @default.
- W2901571414 hasRelatedWork W2061273563 @default.
- W2901571414 hasRelatedWork W2285052147 @default.
- W2901571414 hasRelatedWork W2729514902 @default.
- W2901571414 hasRelatedWork W2773500201 @default.
- W2901571414 hasRelatedWork W2955889502 @default.
- W2901571414 hasRelatedWork W3008648540 @default.
- W2901571414 hasRelatedWork W4287995534 @default.
- W2901571414 hasRelatedWork W4318067874 @default.
- W2901571414 hasRelatedWork W4319301798 @default.
- W2901571414 isParatext "false" @default.
- W2901571414 isRetracted "false" @default.
- W2901571414 magId "2901571414" @default.
- W2901571414 workType "article" @default.