Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015280606> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3015280606 abstract "This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped connections to gather context cues from intermediate convolution layers. The experiments show that FDDWNet only has 0.8M model size, while achieves 60 FPS running speed on a single RTX 2080Ti GPU with a 1024 × 512 input image. The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets." @default.
- W3015280606 created "2020-04-17" @default.
- W3015280606 creator A5004865604 @default.
- W3015280606 creator A5023868028 @default.
- W3015280606 creator A5029552346 @default.
- W3015280606 creator A5037092055 @default.
- W3015280606 creator A5056543646 @default.
- W3015280606 creator A5087193137 @default.
- W3015280606 date "2020-05-01" @default.
- W3015280606 modified "2023-10-17" @default.
- W3015280606 title "FDDWNet: A Lightweight Convolutional Neural Network for Real-Time Semantic Segmentation" @default.
- W3015280606 cites W114517082 @default.
- W3015280606 cites W1536680647 @default.
- W3015280606 cites W2097117768 @default.
- W3015280606 cites W2194775991 @default.
- W3015280606 cites W2340897893 @default.
- W3015280606 cites W2395611524 @default.
- W3015280606 cites W2762439315 @default.
- W3015280606 cites W2894936553 @default.
- W3015280606 cites W2963037989 @default.
- W3015280606 cites W2963125010 @default.
- W3015280606 cites W2964217532 @default.
- W3015280606 doi "https://doi.org/10.1109/icassp40776.2020.9053838" @default.
- W3015280606 hasPublicationYear "2020" @default.
- W3015280606 type Work @default.
- W3015280606 sameAs 3015280606 @default.
- W3015280606 citedByCount "21" @default.
- W3015280606 countsByYear W30152806062020 @default.
- W3015280606 countsByYear W30152806062021 @default.
- W3015280606 countsByYear W30152806062022 @default.
- W3015280606 countsByYear W30152806062023 @default.
- W3015280606 crossrefType "proceedings-article" @default.
- W3015280606 hasAuthorship W3015280606A5004865604 @default.
- W3015280606 hasAuthorship W3015280606A5023868028 @default.
- W3015280606 hasAuthorship W3015280606A5029552346 @default.
- W3015280606 hasAuthorship W3015280606A5037092055 @default.
- W3015280606 hasAuthorship W3015280606A5056543646 @default.
- W3015280606 hasAuthorship W3015280606A5087193137 @default.
- W3015280606 hasConcept C124504099 @default.
- W3015280606 hasConcept C138885662 @default.
- W3015280606 hasConcept C151730666 @default.
- W3015280606 hasConcept C153180895 @default.
- W3015280606 hasConcept C154945302 @default.
- W3015280606 hasConcept C193415008 @default.
- W3015280606 hasConcept C2776214188 @default.
- W3015280606 hasConcept C2776401178 @default.
- W3015280606 hasConcept C2779343474 @default.
- W3015280606 hasConcept C31972630 @default.
- W3015280606 hasConcept C38652104 @default.
- W3015280606 hasConcept C41008148 @default.
- W3015280606 hasConcept C41895202 @default.
- W3015280606 hasConcept C45347329 @default.
- W3015280606 hasConcept C50644808 @default.
- W3015280606 hasConcept C81363708 @default.
- W3015280606 hasConcept C86803240 @default.
- W3015280606 hasConcept C89600930 @default.
- W3015280606 hasConceptScore W3015280606C124504099 @default.
- W3015280606 hasConceptScore W3015280606C138885662 @default.
- W3015280606 hasConceptScore W3015280606C151730666 @default.
- W3015280606 hasConceptScore W3015280606C153180895 @default.
- W3015280606 hasConceptScore W3015280606C154945302 @default.
- W3015280606 hasConceptScore W3015280606C193415008 @default.
- W3015280606 hasConceptScore W3015280606C2776214188 @default.
- W3015280606 hasConceptScore W3015280606C2776401178 @default.
- W3015280606 hasConceptScore W3015280606C2779343474 @default.
- W3015280606 hasConceptScore W3015280606C31972630 @default.
- W3015280606 hasConceptScore W3015280606C38652104 @default.
- W3015280606 hasConceptScore W3015280606C41008148 @default.
- W3015280606 hasConceptScore W3015280606C41895202 @default.
- W3015280606 hasConceptScore W3015280606C45347329 @default.
- W3015280606 hasConceptScore W3015280606C50644808 @default.
- W3015280606 hasConceptScore W3015280606C81363708 @default.
- W3015280606 hasConceptScore W3015280606C86803240 @default.
- W3015280606 hasConceptScore W3015280606C89600930 @default.
- W3015280606 hasLocation W30152806061 @default.
- W3015280606 hasOpenAccess W3015280606 @default.
- W3015280606 hasPrimaryLocation W30152806061 @default.
- W3015280606 hasRelatedWork W11087085 @default.
- W3015280606 hasRelatedWork W13275467 @default.
- W3015280606 hasRelatedWork W14128562 @default.
- W3015280606 hasRelatedWork W2423129 @default.
- W3015280606 hasRelatedWork W274842 @default.
- W3015280606 hasRelatedWork W2864082 @default.
- W3015280606 hasRelatedWork W4044073 @default.
- W3015280606 hasRelatedWork W4518655 @default.
- W3015280606 hasRelatedWork W9190101 @default.
- W3015280606 hasRelatedWork W9952751 @default.
- W3015280606 isParatext "false" @default.
- W3015280606 isRetracted "false" @default.
- W3015280606 magId "3015280606" @default.
- W3015280606 workType "article" @default.