Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996106355> ?p ?o ?g. }
- W2996106355 abstract "Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little awareness of computational efficiency. In this paper, we introduce LiteSeg, a lightweight architecture for semantic image segmentation. In this work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and apply short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model. LiteSeg architecture is introduced and tested with multiple backbone networks as Darknet19, MobileNet, and ShuffleNet to provide multiple trade-offs between accuracy and computational cost. The proposed model LiteSeg, with MobileNetV2 as a backbone network, achieves an accuracy of 67.81% mean intersection over union at 161 frames per second with 640 × 360 resolution on the Cityscapes dataset." @default.
- W2996106355 created "2019-12-26" @default.
- W2996106355 creator A5004204048 @default.
- W2996106355 creator A5013227055 @default.
- W2996106355 creator A5074219072 @default.
- W2996106355 date "2019-12-01" @default.
- W2996106355 modified "2023-09-29" @default.
- W2996106355 title "LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation" @default.
- W2996106355 cites W1745334888 @default.
- W2996106355 cites W1903029394 @default.
- W2996106355 cites W1905829557 @default.
- W2996106355 cites W1927251054 @default.
- W2996106355 cites W1945608308 @default.
- W2996106355 cites W2097117768 @default.
- W2996106355 cites W2194775991 @default.
- W2996106355 cites W2340897893 @default.
- W2996106355 cites W2412782625 @default.
- W2996106355 cites W2549139847 @default.
- W2996106355 cites W2560023338 @default.
- W2996106355 cites W2570343428 @default.
- W2996106355 cites W2740036778 @default.
- W2996106355 cites W2963163009 @default.
- W2996106355 cites W2963351448 @default.
- W2996106355 cites W2963446712 @default.
- W2996106355 cites W2963815618 @default.
- W2996106355 cites W2963881378 @default.
- W2996106355 cites W2963954267 @default.
- W2996106355 cites W4253153980 @default.
- W2996106355 doi "https://doi.org/10.1109/dicta47822.2019.8945975" @default.
- W2996106355 hasPublicationYear "2019" @default.
- W2996106355 type Work @default.
- W2996106355 sameAs 2996106355 @default.
- W2996106355 citedByCount "41" @default.
- W2996106355 countsByYear W29961063552020 @default.
- W2996106355 countsByYear W29961063552021 @default.
- W2996106355 countsByYear W29961063552022 @default.
- W2996106355 countsByYear W29961063552023 @default.
- W2996106355 crossrefType "proceedings-article" @default.
- W2996106355 hasAuthorship W2996106355A5004204048 @default.
- W2996106355 hasAuthorship W2996106355A5013227055 @default.
- W2996106355 hasAuthorship W2996106355A5074219072 @default.
- W2996106355 hasBestOaLocation W29961063552 @default.
- W2996106355 hasConcept C11413529 @default.
- W2996106355 hasConcept C115961682 @default.
- W2996106355 hasConcept C120665830 @default.
- W2996106355 hasConcept C121332964 @default.
- W2996106355 hasConcept C124504099 @default.
- W2996106355 hasConcept C127413603 @default.
- W2996106355 hasConcept C142575187 @default.
- W2996106355 hasConcept C146978453 @default.
- W2996106355 hasConcept C153180895 @default.
- W2996106355 hasConcept C154945302 @default.
- W2996106355 hasConcept C155512373 @default.
- W2996106355 hasConcept C193415008 @default.
- W2996106355 hasConcept C205372480 @default.
- W2996106355 hasConcept C31258907 @default.
- W2996106355 hasConcept C31972630 @default.
- W2996106355 hasConcept C41008148 @default.
- W2996106355 hasConcept C45347329 @default.
- W2996106355 hasConcept C50644808 @default.
- W2996106355 hasConcept C64543145 @default.
- W2996106355 hasConcept C70437156 @default.
- W2996106355 hasConcept C88796919 @default.
- W2996106355 hasConcept C89600930 @default.
- W2996106355 hasConceptScore W2996106355C11413529 @default.
- W2996106355 hasConceptScore W2996106355C115961682 @default.
- W2996106355 hasConceptScore W2996106355C120665830 @default.
- W2996106355 hasConceptScore W2996106355C121332964 @default.
- W2996106355 hasConceptScore W2996106355C124504099 @default.
- W2996106355 hasConceptScore W2996106355C127413603 @default.
- W2996106355 hasConceptScore W2996106355C142575187 @default.
- W2996106355 hasConceptScore W2996106355C146978453 @default.
- W2996106355 hasConceptScore W2996106355C153180895 @default.
- W2996106355 hasConceptScore W2996106355C154945302 @default.
- W2996106355 hasConceptScore W2996106355C155512373 @default.
- W2996106355 hasConceptScore W2996106355C193415008 @default.
- W2996106355 hasConceptScore W2996106355C205372480 @default.
- W2996106355 hasConceptScore W2996106355C31258907 @default.
- W2996106355 hasConceptScore W2996106355C31972630 @default.
- W2996106355 hasConceptScore W2996106355C41008148 @default.
- W2996106355 hasConceptScore W2996106355C45347329 @default.
- W2996106355 hasConceptScore W2996106355C50644808 @default.
- W2996106355 hasConceptScore W2996106355C64543145 @default.
- W2996106355 hasConceptScore W2996106355C70437156 @default.
- W2996106355 hasConceptScore W2996106355C88796919 @default.
- W2996106355 hasConceptScore W2996106355C89600930 @default.
- W2996106355 hasLocation W29961063551 @default.
- W2996106355 hasLocation W29961063552 @default.
- W2996106355 hasOpenAccess W2996106355 @default.
- W2996106355 hasPrimaryLocation W29961063551 @default.
- W2996106355 hasRelatedWork W1669643531 @default.
- W2996106355 hasRelatedWork W2110230079 @default.
- W2996106355 hasRelatedWork W2117933325 @default.
- W2996106355 hasRelatedWork W2122581818 @default.
- W2996106355 hasRelatedWork W2159066190 @default.
- W2996106355 hasRelatedWork W2739874619 @default.
- W2996106355 hasRelatedWork W2920985544 @default.
- W2996106355 hasRelatedWork W2943038984 @default.
- W2996106355 hasRelatedWork W2996106355 @default.
- W2996106355 hasRelatedWork W3212213449 @default.