Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361297371> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4361297371 endingPage "109557" @default.
- W4361297371 startingPage "109557" @default.
- W4361297371 abstract "Recent studies show a significant growth in semantic segmentation. However, many semantic segmentation models still have a large number of parameters, making them unsuitable for resource-constrained embedded devices. To address this issue, we propose an efficient Shared Feature Reuse Segmentation (SFRSeg) model containing several novelties: a new yet effective shared-branch multiple sub-encoders design, a context mining module and a semantic aggregating module for better context granularity. In particular, our shared-branch approach improves the entire feature hierarchy by sharing the spatial and context knowledge in both shallow and deep branches. After every shared point in each sub-encoder, a proposed cascading context mining (CCM) module is deployed to filter out the noisy spatial details from the feature maps and provides a diverse size of receptive fields for capturing the latent context between multi-scale geometric shapes in the scene. To overcome the gradient vanishing issue at the early stage, we reduce the number of layers in the first sub-encoder and employ a unique multiple sub-encoders design which reprocesses the rich global feature maps through multiple sub-encoders for better feature refinement. Later, the rich semantic features generated by the efficient sub-encoders at different levels are fused by the proposed Hybrid Path Attention Semantic Aggregation (HPA-SA) module that effectively reduces the semantic gap between feature maps at different levels and alleviate the well-known boundary degeneration effect. To make it computationally efficient for resource-constrained embedded devices, a series of lightweight methods such as a lightweight encoder, a squeeze-and-excitation design, separable convolution filters, channel reduction (CR) are carefully exploited. With an exceptional performance on Cityscapes (70.6% test mIoU) and CamVid (74.7% test mIoU) data sets, the proposed model is shown to be superior over existing light real-time semantic segmentation models whilst having only 1.6 million parameters." @default.
- W4361297371 created "2023-03-31" @default.
- W4361297371 creator A5004852178 @default.
- W4361297371 creator A5053327787 @default.
- W4361297371 creator A5074727256 @default.
- W4361297371 date "2023-08-01" @default.
- W4361297371 modified "2023-09-26" @default.
- W4361297371 title "A real-time semantic segmentation model using iteratively shared features in multiple sub-encoders" @default.
- W4361297371 cites W2171943915 @default.
- W4361297371 cites W2558580397 @default.
- W4361297371 cites W2743627947 @default.
- W4361297371 cites W2903642350 @default.
- W4361297371 cites W2963881378 @default.
- W4361297371 cites W2996977542 @default.
- W4361297371 cites W3005938789 @default.
- W4361297371 cites W3077024029 @default.
- W4361297371 cites W3196904463 @default.
- W4361297371 cites W3201484072 @default.
- W4361297371 cites W4206312730 @default.
- W4361297371 doi "https://doi.org/10.1016/j.patcog.2023.109557" @default.
- W4361297371 hasPublicationYear "2023" @default.
- W4361297371 type Work @default.
- W4361297371 citedByCount "4" @default.
- W4361297371 countsByYear W43612973712023 @default.
- W4361297371 crossrefType "journal-article" @default.
- W4361297371 hasAuthorship W4361297371A5004852178 @default.
- W4361297371 hasAuthorship W4361297371A5053327787 @default.
- W4361297371 hasAuthorship W4361297371A5074727256 @default.
- W4361297371 hasConcept C111919701 @default.
- W4361297371 hasConcept C118505674 @default.
- W4361297371 hasConcept C138885662 @default.
- W4361297371 hasConcept C151730666 @default.
- W4361297371 hasConcept C153180895 @default.
- W4361297371 hasConcept C154945302 @default.
- W4361297371 hasConcept C2776401178 @default.
- W4361297371 hasConcept C2779343474 @default.
- W4361297371 hasConcept C2781122975 @default.
- W4361297371 hasConcept C41008148 @default.
- W4361297371 hasConcept C41895202 @default.
- W4361297371 hasConcept C86803240 @default.
- W4361297371 hasConcept C89600930 @default.
- W4361297371 hasConceptScore W4361297371C111919701 @default.
- W4361297371 hasConceptScore W4361297371C118505674 @default.
- W4361297371 hasConceptScore W4361297371C138885662 @default.
- W4361297371 hasConceptScore W4361297371C151730666 @default.
- W4361297371 hasConceptScore W4361297371C153180895 @default.
- W4361297371 hasConceptScore W4361297371C154945302 @default.
- W4361297371 hasConceptScore W4361297371C2776401178 @default.
- W4361297371 hasConceptScore W4361297371C2779343474 @default.
- W4361297371 hasConceptScore W4361297371C2781122975 @default.
- W4361297371 hasConceptScore W4361297371C41008148 @default.
- W4361297371 hasConceptScore W4361297371C41895202 @default.
- W4361297371 hasConceptScore W4361297371C86803240 @default.
- W4361297371 hasConceptScore W4361297371C89600930 @default.
- W4361297371 hasLocation W43612973711 @default.
- W4361297371 hasOpenAccess W4361297371 @default.
- W4361297371 hasPrimaryLocation W43612973711 @default.
- W4361297371 hasRelatedWork W2349359195 @default.
- W4361297371 hasRelatedWork W2382607599 @default.
- W4361297371 hasRelatedWork W2532775738 @default.
- W4361297371 hasRelatedWork W2546942002 @default.
- W4361297371 hasRelatedWork W2901189993 @default.
- W4361297371 hasRelatedWork W2970216048 @default.
- W4361297371 hasRelatedWork W3133882761 @default.
- W4361297371 hasRelatedWork W3177203279 @default.
- W4361297371 hasRelatedWork W4293801829 @default.
- W4361297371 hasRelatedWork W4312773091 @default.
- W4361297371 hasVolume "140" @default.
- W4361297371 isParatext "false" @default.
- W4361297371 isRetracted "false" @default.
- W4361297371 workType "article" @default.