FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384341724> ?p ?o ?g. }

• W4384341724 endingPage "6382" @default.
• W4384341724 startingPage "6382" @default.
• W4384341724 abstract "Currently, real-time semantic segmentation networks are intensely demanded in resource-constrained practical applications, such as mobile devices, drones and autonomous driving systems. However, most of the current popular approaches have difficulty in obtaining sufficiently large receptive fields, and they sacrifice low-level details to improve inference speed, leading to decreased segmentation accuracy. In this paper, a lightweight and efficient multi-level feature adaptive fusion network (MFAFNet) is proposed to address this problem. Specifically, we design a separable asymmetric reinforcement non-bottleneck module, which designs a parallel structure to extract short- and long-range contextual information and use optimized convolution to increase the inference speed. In addition, we propose a feature adaptive fusion module that effectively balances feature maps with multiple resolutions to reduce the loss of spatial detail information. We evaluate our model with state-of-the-art real-time semantic segmentation methods on the Cityscapes and Camvid datasets. Without any pre-training and post-processing, our MFAFNet has only 1.27 M parameters, while achieving accuracies of 75.9% and 69.9% mean IoU with speeds of 60.1 and 82.6 FPS on the Cityscapes and Camvid test sets, respectively. The experimental results demonstrate that the proposed method achieves an excellent trade-off between inference speed, segmentation accuracy and model size." @default.
• W4384341724 created "2023-07-15" @default.
• W4384341724 creator A5014708963 @default.
• W4384341724 creator A5043307748 @default.
• W4384341724 creator A5054232978 @default.
• W4384341724 creator A5078094074 @default.
• W4384341724 date "2023-07-13" @default.
• W4384341724 modified "2023-09-27" @default.
• W4384341724 title "MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation" @default.
• W4384341724 cites W2171943915 @default.
• W4384341724 cites W2340897893 @default.
• W4384341724 cites W2560023338 @default.
• W4384341724 cites W2762439315 @default.
• W4384341724 cites W2883780447 @default.
• W4384341724 cites W2888270240 @default.
• W4384341724 cites W2962772649 @default.
• W4384341724 cites W2963163009 @default.
• W4384341724 cites W2963419596 @default.
• W4384341724 cites W2963516811 @default.
• W4384341724 cites W2964217532 @default.
• W4384341724 cites W2985269212 @default.
• W4384341724 cites W3039156183 @default.
• W4384341724 cites W3082097505 @default.
• W4384341724 cites W3112503277 @default.
• W4384341724 cites W3128036635 @default.
• W4384341724 cites W3132531378 @default.
• W4384341724 cites W3138038780 @default.
• W4384341724 cites W3158385340 @default.
• W4384341724 cites W3159640305 @default.
• W4384341724 cites W3159837173 @default.
• W4384341724 cites W3169865585 @default.
• W4384341724 cites W3171275468 @default.
• W4384341724 cites W3177791215 @default.
• W4384341724 cites W3181267127 @default.
• W4384341724 cites W3190437803 @default.
• W4384341724 cites W3196904463 @default.
• W4384341724 cites W4200415850 @default.
• W4384341724 cites W4207065174 @default.
• W4384341724 cites W4210643638 @default.
• W4384341724 cites W4225674167 @default.
• W4384341724 cites W4308621049 @default.
• W4384341724 cites W4311759245 @default.
• W4384341724 cites W4320036829 @default.
• W4384341724 cites W4320879405 @default.
• W4384341724 cites W4327923876 @default.
• W4384341724 cites W4379206867 @default.
• W4384341724 doi "https://doi.org/10.3390/s23146382" @default.
• W4384341724 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37514676" @default.
• W4384341724 hasPublicationYear "2023" @default.
• W4384341724 type Work @default.
• W4384341724 citedByCount "0" @default.
• W4384341724 crossrefType "journal-article" @default.
• W4384341724 hasAuthorship W4384341724A5014708963 @default.
• W4384341724 hasAuthorship W4384341724A5043307748 @default.
• W4384341724 hasAuthorship W4384341724A5054232978 @default.
• W4384341724 hasAuthorship W4384341724A5078094074 @default.
• W4384341724 hasBestOaLocation W43843417241 @default.
• W4384341724 hasConcept C138885662 @default.
• W4384341724 hasConcept C149635348 @default.
• W4384341724 hasConcept C153180895 @default.
• W4384341724 hasConcept C154945302 @default.
• W4384341724 hasConcept C2776214188 @default.
• W4384341724 hasConcept C2776401178 @default.
• W4384341724 hasConcept C2780513914 @default.
• W4384341724 hasConcept C41008148 @default.
• W4384341724 hasConcept C41895202 @default.
• W4384341724 hasConcept C45347329 @default.
• W4384341724 hasConcept C50644808 @default.
• W4384341724 hasConcept C81363708 @default.
• W4384341724 hasConcept C89600930 @default.
• W4384341724 hasConceptScore W4384341724C138885662 @default.
• W4384341724 hasConceptScore W4384341724C149635348 @default.
• W4384341724 hasConceptScore W4384341724C153180895 @default.
• W4384341724 hasConceptScore W4384341724C154945302 @default.
• W4384341724 hasConceptScore W4384341724C2776214188 @default.
• W4384341724 hasConceptScore W4384341724C2776401178 @default.
• W4384341724 hasConceptScore W4384341724C2780513914 @default.
• W4384341724 hasConceptScore W4384341724C41008148 @default.
• W4384341724 hasConceptScore W4384341724C41895202 @default.
• W4384341724 hasConceptScore W4384341724C45347329 @default.
• W4384341724 hasConceptScore W4384341724C50644808 @default.
• W4384341724 hasConceptScore W4384341724C81363708 @default.
• W4384341724 hasConceptScore W4384341724C89600930 @default.
• W4384341724 hasIssue "14" @default.
• W4384341724 hasLocation W43843417241 @default.
• W4384341724 hasLocation W43843417242 @default.
• W4384341724 hasLocation W43843417243 @default.
• W4384341724 hasOpenAccess W4384341724 @default.
• W4384341724 hasPrimaryLocation W43843417241 @default.
• W4384341724 hasRelatedWork W2295021132 @default.
• W4384341724 hasRelatedWork W2532775738 @default.
• W4384341724 hasRelatedWork W2766634277 @default.
• W4384341724 hasRelatedWork W2767651786 @default.
• W4384341724 hasRelatedWork W2890372105 @default.
• W4384341724 hasRelatedWork W2912288872 @default.
• W4384341724 hasRelatedWork W3106036237 @default.
• W4384341724 hasRelatedWork W4200528772 @default.
• W4384341724 hasRelatedWork W4312417841 @default.

• next