Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387454352> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4387454352 abstract "Abstract Transformer together with convolutional neural network (CNN) has achieved better performance than the pure module-based methods. However, the advantages of both coding styles are not well considered, and the designed fusion modules have not achieved good effect in the aspect of remote sensing image (RSI) semantic segmentation. In this paper, to exploit local and global pixel dependencies, improved Gated Recurrent Units combined with fusion, are proposed to harness the complementary advantages of Parallel Hybrid Network for semantic segmentation of RSIs. The proposed network core is feature selection and fusion module (FSFM), which is composed by both feature selection units (FSU) and feature fusion units (FFU), named FSFM-PHN. Concretely, to precisely incorporate local and global representations, the improved reset and update gates of ConvGRU are treated as FSU and is realized the feature selection of the advantageous segmentation task. To merge the outputs from ResNet, Swin Transformer and FSU, feature fusion units (FFU) based on stack and sequential convolutional block operations is constructed. On the public Vaihingen, Potsdam and BLU datasets, the experimental results show that FSFM is effective, which outperforms state-of-the-art methods in some famous remote image semantic segmentation tasks." @default.
- W4387454352 created "2023-10-10" @default.
- W4387454352 creator A5043683058 @default.
- W4387454352 creator A5060730056 @default.
- W4387454352 creator A5077219678 @default.
- W4387454352 creator A5089657946 @default.
- W4387454352 date "2023-10-09" @default.
- W4387454352 modified "2023-10-11" @default.
- W4387454352 title "Improved Gated Recurrent Units together with Fusion for Semantic Segmentation of Remote Sensing Images based on Parallel Hybrid Network" @default.
- W4387454352 cites W2888358068 @default.
- W4387454352 cites W3017971322 @default.
- W4387454352 cites W3018169007 @default.
- W4387454352 cites W3019131160 @default.
- W4387454352 cites W3093142463 @default.
- W4387454352 cites W3103092912 @default.
- W4387454352 cites W3137308428 @default.
- W4387454352 cites W3142500263 @default.
- W4387454352 cites W3168491317 @default.
- W4387454352 cites W3202923600 @default.
- W4387454352 cites W4205138939 @default.
- W4387454352 cites W4221015298 @default.
- W4387454352 cites W4221166146 @default.
- W4387454352 cites W4226013274 @default.
- W4387454352 cites W4283450732 @default.
- W4387454352 cites W4286203389 @default.
- W4387454352 cites W4378373424 @default.
- W4387454352 cites W4381435453 @default.
- W4387454352 doi "https://doi.org/10.21203/rs.3.rs-3400980/v1" @default.
- W4387454352 hasPublicationYear "2023" @default.
- W4387454352 type Work @default.
- W4387454352 citedByCount "0" @default.
- W4387454352 crossrefType "posted-content" @default.
- W4387454352 hasAuthorship W4387454352A5043683058 @default.
- W4387454352 hasAuthorship W4387454352A5060730056 @default.
- W4387454352 hasAuthorship W4387454352A5077219678 @default.
- W4387454352 hasAuthorship W4387454352A5089657946 @default.
- W4387454352 hasBestOaLocation W43874543521 @default.
- W4387454352 hasConcept C119599485 @default.
- W4387454352 hasConcept C127413603 @default.
- W4387454352 hasConcept C138885662 @default.
- W4387454352 hasConcept C153180895 @default.
- W4387454352 hasConcept C154945302 @default.
- W4387454352 hasConcept C165801399 @default.
- W4387454352 hasConcept C197129107 @default.
- W4387454352 hasConcept C23123220 @default.
- W4387454352 hasConcept C2776401178 @default.
- W4387454352 hasConcept C31972630 @default.
- W4387454352 hasConcept C41008148 @default.
- W4387454352 hasConcept C41895202 @default.
- W4387454352 hasConcept C66322947 @default.
- W4387454352 hasConcept C81363708 @default.
- W4387454352 hasConcept C89600930 @default.
- W4387454352 hasConceptScore W4387454352C119599485 @default.
- W4387454352 hasConceptScore W4387454352C127413603 @default.
- W4387454352 hasConceptScore W4387454352C138885662 @default.
- W4387454352 hasConceptScore W4387454352C153180895 @default.
- W4387454352 hasConceptScore W4387454352C154945302 @default.
- W4387454352 hasConceptScore W4387454352C165801399 @default.
- W4387454352 hasConceptScore W4387454352C197129107 @default.
- W4387454352 hasConceptScore W4387454352C23123220 @default.
- W4387454352 hasConceptScore W4387454352C2776401178 @default.
- W4387454352 hasConceptScore W4387454352C31972630 @default.
- W4387454352 hasConceptScore W4387454352C41008148 @default.
- W4387454352 hasConceptScore W4387454352C41895202 @default.
- W4387454352 hasConceptScore W4387454352C66322947 @default.
- W4387454352 hasConceptScore W4387454352C81363708 @default.
- W4387454352 hasConceptScore W4387454352C89600930 @default.
- W4387454352 hasLocation W43874543521 @default.
- W4387454352 hasOpenAccess W4387454352 @default.
- W4387454352 hasPrimaryLocation W43874543521 @default.
- W4387454352 hasRelatedWork W2354081742 @default.
- W4387454352 hasRelatedWork W2372661603 @default.
- W4387454352 hasRelatedWork W2382112581 @default.
- W4387454352 hasRelatedWork W2383231640 @default.
- W4387454352 hasRelatedWork W2389591058 @default.
- W4387454352 hasRelatedWork W2588987760 @default.
- W4387454352 hasRelatedWork W3124036233 @default.
- W4387454352 hasRelatedWork W4234886518 @default.
- W4387454352 hasRelatedWork W4293226380 @default.
- W4387454352 hasRelatedWork W1785572788 @default.
- W4387454352 isParatext "false" @default.
- W4387454352 isRetracted "false" @default.
- W4387454352 workType "article" @default.