Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313194280> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4313194280 abstract "Encoder-Decoder networks based on local convolutions have shown state-of-the-art results on various medical image segmentation tasks. However, they have limited ability to capture long-range spatial contexts, which has intrigued the development of Transformers with attention mechanisms. Despite their success, Transformers usually have limitations in processing huge medical image volume data due to their high computational complexity and relying on large-scale pre-training. Hence, we introduce a hybrid encoder-decoder, which utilizes both lightweight convolution modules and an axial-spatial transformer (AST) module in the encoder. To capture better multi-view and multi-scale features, we intergrade axial and spatial attention in the AST module to learn long-range dependencies. Meanwhile, convolution operations extract local dependencies and rich local features. Compared to pure vision transformers, the hybrid model has much fewer learnable parameters, which is desirable for clinical usage. The experimental results on three challenging benchmarks demonstrate the competitive performance of the proposed model over the state of the arts." @default.
- W4313194280 created "2023-01-06" @default.
- W4313194280 creator A5002811823 @default.
- W4313194280 creator A5044687301 @default.
- W4313194280 creator A5068717201 @default.
- W4313194280 date "2022-08-21" @default.
- W4313194280 modified "2023-10-18" @default.
- W4313194280 title "AST-Net: Lightweight Hybrid Transformer for Multimodal Brain Tumor Segmentation" @default.
- W4313194280 cites W1641498739 @default.
- W4313194280 cites W1903029394 @default.
- W4313194280 cites W2098056602 @default.
- W4313194280 cites W2412782625 @default.
- W4313194280 cites W2608353599 @default.
- W4313194280 cites W2884585870 @default.
- W4313194280 cites W2909190480 @default.
- W4313194280 cites W2911612027 @default.
- W4313194280 cites W2914493539 @default.
- W4313194280 cites W2962914239 @default.
- W4313194280 cites W2964980777 @default.
- W4313194280 cites W3030952871 @default.
- W4313194280 cites W3035665735 @default.
- W4313194280 cites W3044256341 @default.
- W4313194280 cites W3097065222 @default.
- W4313194280 cites W3102474308 @default.
- W4313194280 cites W3128046250 @default.
- W4313194280 cites W3132455321 @default.
- W4313194280 cites W3137456187 @default.
- W4313194280 cites W3138516171 @default.
- W4313194280 cites W3142164167 @default.
- W4313194280 cites W3149181558 @default.
- W4313194280 cites W3149990595 @default.
- W4313194280 cites W3162408150 @default.
- W4313194280 cites W3168236164 @default.
- W4313194280 cites W3203841574 @default.
- W4313194280 cites W3204614423 @default.
- W4313194280 cites W4212875960 @default.
- W4313194280 doi "https://doi.org/10.1109/icpr56361.2022.9956705" @default.
- W4313194280 hasPublicationYear "2022" @default.
- W4313194280 type Work @default.
- W4313194280 citedByCount "1" @default.
- W4313194280 countsByYear W43131942802023 @default.
- W4313194280 crossrefType "proceedings-article" @default.
- W4313194280 hasAuthorship W4313194280A5002811823 @default.
- W4313194280 hasAuthorship W4313194280A5044687301 @default.
- W4313194280 hasAuthorship W4313194280A5068717201 @default.
- W4313194280 hasConcept C111919701 @default.
- W4313194280 hasConcept C113775141 @default.
- W4313194280 hasConcept C118505674 @default.
- W4313194280 hasConcept C119599485 @default.
- W4313194280 hasConcept C124504099 @default.
- W4313194280 hasConcept C127413603 @default.
- W4313194280 hasConcept C153180895 @default.
- W4313194280 hasConcept C154945302 @default.
- W4313194280 hasConcept C165801399 @default.
- W4313194280 hasConcept C31972630 @default.
- W4313194280 hasConcept C41008148 @default.
- W4313194280 hasConcept C66322947 @default.
- W4313194280 hasConcept C89600930 @default.
- W4313194280 hasConcept C9390403 @default.
- W4313194280 hasConceptScore W4313194280C111919701 @default.
- W4313194280 hasConceptScore W4313194280C113775141 @default.
- W4313194280 hasConceptScore W4313194280C118505674 @default.
- W4313194280 hasConceptScore W4313194280C119599485 @default.
- W4313194280 hasConceptScore W4313194280C124504099 @default.
- W4313194280 hasConceptScore W4313194280C127413603 @default.
- W4313194280 hasConceptScore W4313194280C153180895 @default.
- W4313194280 hasConceptScore W4313194280C154945302 @default.
- W4313194280 hasConceptScore W4313194280C165801399 @default.
- W4313194280 hasConceptScore W4313194280C31972630 @default.
- W4313194280 hasConceptScore W4313194280C41008148 @default.
- W4313194280 hasConceptScore W4313194280C66322947 @default.
- W4313194280 hasConceptScore W4313194280C89600930 @default.
- W4313194280 hasConceptScore W4313194280C9390403 @default.
- W4313194280 hasLocation W43131942801 @default.
- W4313194280 hasOpenAccess W4313194280 @default.
- W4313194280 hasPrimaryLocation W43131942801 @default.
- W4313194280 hasRelatedWork W1669643531 @default.
- W4313194280 hasRelatedWork W1700740617 @default.
- W4313194280 hasRelatedWork W1721780360 @default.
- W4313194280 hasRelatedWork W2110230079 @default.
- W4313194280 hasRelatedWork W2117664411 @default.
- W4313194280 hasRelatedWork W2117933325 @default.
- W4313194280 hasRelatedWork W2122581818 @default.
- W4313194280 hasRelatedWork W2159066190 @default.
- W4313194280 hasRelatedWork W2739874619 @default.
- W4313194280 hasRelatedWork W1967061043 @default.
- W4313194280 isParatext "false" @default.
- W4313194280 isRetracted "false" @default.
- W4313194280 workType "article" @default.