Matches in SemOpenAlex for { <https://semopenalex.org/work/W2610528085> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2610528085 endingPage "446" @default.
- W2610528085 startingPage "446" @default.
- W2610528085 abstract "Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this task quite challenging. Recently, deep convolutional neural networks (DCNNs) have shown outstanding performance in this task. A common strategy of these methods (e.g., SegNet) for performance improvement is to combine the feature maps learned at different DCNN layers. However, such a combination is usually implemented via feature map summation or concatenation, indicating that the features are considered indiscriminately. In fact, features at different positions contribute differently to the final performance. It is advantageous to automatically select adaptive features when merging different-layer feature maps. To achieve this goal, we propose a gated convolutional neural network to fulfill this task. Specifically, we explore the relationship between the information entropy of the feature maps and the label-error map, and then a gate mechanism is embedded to integrate the feature maps more effectively. The gate is implemented by the entropy maps, which are generated to assign adaptive weights to different feature maps as their relative importance. Generally, the entropy maps, i.e., the gates, guide the network to focus on the highly-uncertain pixels, where detailed information from lower layers is required to improve the separability of these pixels. The selected features are finally combined to feed into the classifier layer, which predicts the semantic label of each pixel. The proposed method achieves competitive segmentation accuracy on the public ISPRS 2D Semantic Labeling benchmark, which is challenging for segmentation by only using the RGB images." @default.
- W2610528085 created "2017-05-12" @default.
- W2610528085 creator A5008532496 @default.
- W2610528085 creator A5018863416 @default.
- W2610528085 creator A5040673285 @default.
- W2610528085 creator A5052441498 @default.
- W2610528085 creator A5072815126 @default.
- W2610528085 date "2017-05-05" @default.
- W2610528085 modified "2023-10-17" @default.
- W2610528085 title "Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images" @default.
- W2610528085 cites W1498436455 @default.
- W2610528085 cites W1799946925 @default.
- W2610528085 cites W1837697898 @default.
- W2610528085 cites W1990372984 @default.
- W2610528085 cites W2034906331 @default.
- W2610528085 cites W2064675550 @default.
- W2610528085 cites W2106277226 @default.
- W2610528085 cites W2117539524 @default.
- W2610528085 cites W2288723698 @default.
- W2610528085 cites W2316226477 @default.
- W2610528085 cites W2412588858 @default.
- W2610528085 cites W2412782625 @default.
- W2610528085 cites W2593542728 @default.
- W2610528085 doi "https://doi.org/10.3390/rs9050446" @default.
- W2610528085 hasPublicationYear "2017" @default.
- W2610528085 type Work @default.
- W2610528085 sameAs 2610528085 @default.
- W2610528085 citedByCount "154" @default.
- W2610528085 countsByYear W26105280852017 @default.
- W2610528085 countsByYear W26105280852018 @default.
- W2610528085 countsByYear W26105280852019 @default.
- W2610528085 countsByYear W26105280852020 @default.
- W2610528085 countsByYear W26105280852021 @default.
- W2610528085 countsByYear W26105280852022 @default.
- W2610528085 countsByYear W26105280852023 @default.
- W2610528085 crossrefType "journal-article" @default.
- W2610528085 hasAuthorship W2610528085A5008532496 @default.
- W2610528085 hasAuthorship W2610528085A5018863416 @default.
- W2610528085 hasAuthorship W2610528085A5040673285 @default.
- W2610528085 hasAuthorship W2610528085A5052441498 @default.
- W2610528085 hasAuthorship W2610528085A5072815126 @default.
- W2610528085 hasBestOaLocation W26105280851 @default.
- W2610528085 hasConcept C138885662 @default.
- W2610528085 hasConcept C153180895 @default.
- W2610528085 hasConcept C154945302 @default.
- W2610528085 hasConcept C160633673 @default.
- W2610528085 hasConcept C2776401178 @default.
- W2610528085 hasConcept C41008148 @default.
- W2610528085 hasConcept C41895202 @default.
- W2610528085 hasConcept C81363708 @default.
- W2610528085 hasConcept C82990744 @default.
- W2610528085 hasConcept C89600930 @default.
- W2610528085 hasConcept C95623464 @default.
- W2610528085 hasConceptScore W2610528085C138885662 @default.
- W2610528085 hasConceptScore W2610528085C153180895 @default.
- W2610528085 hasConceptScore W2610528085C154945302 @default.
- W2610528085 hasConceptScore W2610528085C160633673 @default.
- W2610528085 hasConceptScore W2610528085C2776401178 @default.
- W2610528085 hasConceptScore W2610528085C41008148 @default.
- W2610528085 hasConceptScore W2610528085C41895202 @default.
- W2610528085 hasConceptScore W2610528085C81363708 @default.
- W2610528085 hasConceptScore W2610528085C82990744 @default.
- W2610528085 hasConceptScore W2610528085C89600930 @default.
- W2610528085 hasConceptScore W2610528085C95623464 @default.
- W2610528085 hasFunder F4320321001 @default.
- W2610528085 hasFunder F4320322919 @default.
- W2610528085 hasIssue "5" @default.
- W2610528085 hasLocation W26105280851 @default.
- W2610528085 hasOpenAccess W2610528085 @default.
- W2610528085 hasPrimaryLocation W26105280851 @default.
- W2610528085 hasRelatedWork W1982025852 @default.
- W2610528085 hasRelatedWork W2053596378 @default.
- W2610528085 hasRelatedWork W2085033728 @default.
- W2610528085 hasRelatedWork W2106540031 @default.
- W2610528085 hasRelatedWork W2168523118 @default.
- W2610528085 hasRelatedWork W2171299904 @default.
- W2610528085 hasRelatedWork W2922442631 @default.
- W2610528085 hasRelatedWork W4285411112 @default.
- W2610528085 hasRelatedWork W4293226380 @default.
- W2610528085 hasRelatedWork W4313906399 @default.
- W2610528085 hasVolume "9" @default.
- W2610528085 isParatext "false" @default.
- W2610528085 isRetracted "false" @default.
- W2610528085 magId "2610528085" @default.
- W2610528085 workType "article" @default.