Matches in SemOpenAlex for { <https://semopenalex.org/work/W2917191389> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2917191389 abstract "In this work we consider the application of convolutional neural networks (CNNs) for pixel-wise labeling (a.k.a., semantic segmentation) of remote sensing imagery (e.g., aerial color or hyperspectral imagery). Remote sensing imagery is usually stored in the form of very large images, referred to as tiles, which are too large to be segmented directly using most CNNs and their associated hardware. As a result, during label inference, smaller sub-images, called patches, are processed individually and then stitched (concatenated) back together to create a tile-sized label map. This approach suffers from computational ineffiency and can result in discontinuities at output boundaries. We propose a simple alternative approach in which the input size of the CNN is dramatically increased only during label inference. This does not avoid stitching altogether, but substantially mitigates its limitations. We evaluate the performance of the proposed approach against a vonventional stitching approach using two popular segmentation CNN models and two large-scale remote sensing imagery datasets. The results suggest that the proposed approach substantially reduces label inference time, while also yielding modest overall label accuracy increases. This approach contributed to our wining entry (overall performance) in the INRIA building labeling competition." @default.
- W2917191389 created "2019-03-02" @default.
- W2917191389 creator A5004578492 @default.
- W2917191389 creator A5007239332 @default.
- W2917191389 creator A5054438743 @default.
- W2917191389 creator A5081855980 @default.
- W2917191389 creator A5084623752 @default.
- W2917191389 date "2018-05-30" @default.
- W2917191389 modified "2023-09-27" @default.
- W2917191389 title "Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations" @default.
- W2917191389 cites W1686810756 @default.
- W2917191389 cites W1901129140 @default.
- W2917191389 cites W2031489346 @default.
- W2917191389 cites W2194775991 @default.
- W2917191389 cites W2305495461 @default.
- W2917191389 cites W2412782625 @default.
- W2917191389 cites W2469938794 @default.
- W2917191389 cites W2488187315 @default.
- W2917191389 cites W2494424066 @default.
- W2917191389 cites W2527276685 @default.
- W2917191389 cites W2536614103 @default.
- W2917191389 cites W2560023338 @default.
- W2917191389 cites W2610528085 @default.
- W2917191389 cites W2630837129 @default.
- W2917191389 cites W2683784395 @default.
- W2917191389 cites W2782784141 @default.
- W2917191389 cites W2949533892 @default.
- W2917191389 cites W2950305897 @default.
- W2917191389 cites W2963659230 @default.
- W2917191389 cites W2964121744 @default.
- W2917191389 cites W3105127913 @default.
- W2917191389 hasPublicationYear "2018" @default.
- W2917191389 type Work @default.
- W2917191389 sameAs 2917191389 @default.
- W2917191389 citedByCount "0" @default.
- W2917191389 crossrefType "posted-content" @default.
- W2917191389 hasAuthorship W2917191389A5004578492 @default.
- W2917191389 hasAuthorship W2917191389A5007239332 @default.
- W2917191389 hasAuthorship W2917191389A5054438743 @default.
- W2917191389 hasAuthorship W2917191389A5081855980 @default.
- W2917191389 hasAuthorship W2917191389A5084623752 @default.
- W2917191389 hasConcept C153180895 @default.
- W2917191389 hasConcept C154945302 @default.
- W2917191389 hasConcept C159078339 @default.
- W2917191389 hasConcept C160633673 @default.
- W2917191389 hasConcept C2776214188 @default.
- W2917191389 hasConcept C29081049 @default.
- W2917191389 hasConcept C31972630 @default.
- W2917191389 hasConcept C41008148 @default.
- W2917191389 hasConcept C48044578 @default.
- W2917191389 hasConcept C77088390 @default.
- W2917191389 hasConcept C81363708 @default.
- W2917191389 hasConcept C89600930 @default.
- W2917191389 hasConceptScore W2917191389C153180895 @default.
- W2917191389 hasConceptScore W2917191389C154945302 @default.
- W2917191389 hasConceptScore W2917191389C159078339 @default.
- W2917191389 hasConceptScore W2917191389C160633673 @default.
- W2917191389 hasConceptScore W2917191389C2776214188 @default.
- W2917191389 hasConceptScore W2917191389C29081049 @default.
- W2917191389 hasConceptScore W2917191389C31972630 @default.
- W2917191389 hasConceptScore W2917191389C41008148 @default.
- W2917191389 hasConceptScore W2917191389C48044578 @default.
- W2917191389 hasConceptScore W2917191389C77088390 @default.
- W2917191389 hasConceptScore W2917191389C81363708 @default.
- W2917191389 hasConceptScore W2917191389C89600930 @default.
- W2917191389 hasLocation W29171913891 @default.
- W2917191389 hasOpenAccess W2917191389 @default.
- W2917191389 hasPrimaryLocation W29171913891 @default.
- W2917191389 hasRelatedWork W1901129140 @default.
- W2917191389 hasRelatedWork W2295018589 @default.
- W2917191389 hasRelatedWork W2399168535 @default.
- W2917191389 hasRelatedWork W2793116851 @default.
- W2917191389 hasRelatedWork W2794930662 @default.
- W2917191389 hasRelatedWork W2890080153 @default.
- W2917191389 hasRelatedWork W2901786613 @default.
- W2917191389 hasRelatedWork W2998317038 @default.
- W2917191389 hasRelatedWork W3006759678 @default.
- W2917191389 hasRelatedWork W3007314771 @default.
- W2917191389 hasRelatedWork W3044776120 @default.
- W2917191389 hasRelatedWork W3113396770 @default.
- W2917191389 hasRelatedWork W3122184312 @default.
- W2917191389 hasRelatedWork W3129806918 @default.
- W2917191389 hasRelatedWork W3158174051 @default.
- W2917191389 hasRelatedWork W3167622021 @default.
- W2917191389 hasRelatedWork W3175551454 @default.
- W2917191389 hasRelatedWork W3186742890 @default.
- W2917191389 hasRelatedWork W3206043367 @default.
- W2917191389 hasRelatedWork W3178603719 @default.
- W2917191389 isParatext "false" @default.
- W2917191389 isRetracted "false" @default.
- W2917191389 magId "2917191389" @default.
- W2917191389 workType "article" @default.