Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386598399> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386598399 abstract "In recent years, accurate models for image segmentation have become larger and more complex. However, it is hard to apply them into embedded devices which usually have limited space for data, energy and computing. Meanwhile, since many embedded devices do not support modifications of computing units, simple models with such requirements cannot be adapted to these devices. To achieve high accuracy for image segmentation in embedded devices, we propose a light-weight and efficient neural network, named Fibonet. Fibonet is constructed by cascading two Fiboblocks, with the Fibonacci structure which adjusts the combination of basic computing units through skip connections and feature reusing so that it is less computationally intensive and dataset-demanding. The experiments demonstrate that Fibonet can be embedded to the mobile terminal for real-time segmentation and can effectively balance accuracy and computing resources. Compared with Resnet18, Fibonet achieves 10.8% higher accuracy performance (mIoU: 0.533 vs. 0.481) with 84.4% fewer parameters (0.441M vs. 2.82M) using similar model width and depth." @default.
- W4386598399 created "2023-09-12" @default.
- W4386598399 creator A5014691053 @default.
- W4386598399 creator A5026631146 @default.
- W4386598399 creator A5029661830 @default.
- W4386598399 creator A5030699864 @default.
- W4386598399 creator A5076613417 @default.
- W4386598399 creator A5085450781 @default.
- W4386598399 date "2023-10-08" @default.
- W4386598399 modified "2023-09-27" @default.
- W4386598399 title "Fibonet: A Light-weight and Efficient Neural Network for Image Segmentation" @default.
- W4386598399 cites W1903029394 @default.
- W4386598399 cites W2037953894 @default.
- W4386598399 cites W2194775991 @default.
- W4386598399 cites W2412782625 @default.
- W4386598399 cites W2560023338 @default.
- W4386598399 cites W2596001200 @default.
- W4386598399 cites W2794460218 @default.
- W4386598399 cites W2883780447 @default.
- W4386598399 cites W2934262148 @default.
- W4386598399 cites W2950784811 @default.
- W4386598399 cites W2962914239 @default.
- W4386598399 cites W2963125010 @default.
- W4386598399 cites W2963163009 @default.
- W4386598399 cites W2963351448 @default.
- W4386598399 cites W2963446712 @default.
- W4386598399 cites W2963925437 @default.
- W4386598399 cites W3031794591 @default.
- W4386598399 cites W3170841864 @default.
- W4386598399 doi "https://doi.org/10.1109/icip49359.2023.10222857" @default.
- W4386598399 hasPublicationYear "2023" @default.
- W4386598399 type Work @default.
- W4386598399 citedByCount "0" @default.
- W4386598399 crossrefType "proceedings-article" @default.
- W4386598399 hasAuthorship W4386598399A5014691053 @default.
- W4386598399 hasAuthorship W4386598399A5026631146 @default.
- W4386598399 hasAuthorship W4386598399A5029661830 @default.
- W4386598399 hasAuthorship W4386598399A5030699864 @default.
- W4386598399 hasAuthorship W4386598399A5076613417 @default.
- W4386598399 hasAuthorship W4386598399A5085450781 @default.
- W4386598399 hasBestOaLocation W43865983991 @default.
- W4386598399 hasConcept C111919701 @default.
- W4386598399 hasConcept C115961682 @default.
- W4386598399 hasConcept C124504099 @default.
- W4386598399 hasConcept C138885662 @default.
- W4386598399 hasConcept C153180895 @default.
- W4386598399 hasConcept C154945302 @default.
- W4386598399 hasConcept C186967261 @default.
- W4386598399 hasConcept C2776401178 @default.
- W4386598399 hasConcept C41008148 @default.
- W4386598399 hasConcept C41895202 @default.
- W4386598399 hasConcept C50644808 @default.
- W4386598399 hasConcept C89600930 @default.
- W4386598399 hasConceptScore W4386598399C111919701 @default.
- W4386598399 hasConceptScore W4386598399C115961682 @default.
- W4386598399 hasConceptScore W4386598399C124504099 @default.
- W4386598399 hasConceptScore W4386598399C138885662 @default.
- W4386598399 hasConceptScore W4386598399C153180895 @default.
- W4386598399 hasConceptScore W4386598399C154945302 @default.
- W4386598399 hasConceptScore W4386598399C186967261 @default.
- W4386598399 hasConceptScore W4386598399C2776401178 @default.
- W4386598399 hasConceptScore W4386598399C41008148 @default.
- W4386598399 hasConceptScore W4386598399C41895202 @default.
- W4386598399 hasConceptScore W4386598399C50644808 @default.
- W4386598399 hasConceptScore W4386598399C89600930 @default.
- W4386598399 hasLocation W43865983991 @default.
- W4386598399 hasOpenAccess W4386598399 @default.
- W4386598399 hasPrimaryLocation W43865983991 @default.
- W4386598399 hasRelatedWork W134976887 @default.
- W4386598399 hasRelatedWork W1582206143 @default.
- W4386598399 hasRelatedWork W2138214894 @default.
- W4386598399 hasRelatedWork W2532775738 @default.
- W4386598399 hasRelatedWork W2546942002 @default.
- W4386598399 hasRelatedWork W2549765251 @default.
- W4386598399 hasRelatedWork W2734888972 @default.
- W4386598399 hasRelatedWork W2970216048 @default.
- W4386598399 hasRelatedWork W3027394838 @default.
- W4386598399 hasRelatedWork W3161321444 @default.
- W4386598399 isParatext "false" @default.
- W4386598399 isRetracted "false" @default.
- W4386598399 workType "article" @default.