Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211614> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4387211614 endingPage "490" @default.
- W4387211614 startingPage "481" @default.
- W4387211614 abstract "Transformer and its variants have been widely used for medical image segmentation. However, the large number of parameter and computational load of these models make them unsuitable for mobile health applications. To address this issue, we propose a more efficient approach, the Efficient Group Enhanced UNet (EGE-UNet). We incorporate a Group multi-axis Hadamard Product Attention module (GHPA) and a Group Aggregation Bridge module (GAB) in a lightweight manner. The GHPA groups input features and performs Hadamard Product Attention mechanism (HPA) on different axes to extract pathological information from diverse perspectives. The GAB effectively fuses multi-scale information by grouping low-level features, high-level features, and a mask generated by the decoder at each stage. Comprehensive experiments on the ISIC2017 and ISIC2018 datasets demonstrate that EGE-UNet outperforms existing state-of-the-art methods. In short, compared to the TransFuse, our model achieves superior segmentation performance while reducing parameter and computation costs by 494x and 160x, respectively. Moreover, to our best knowledge, this is the first model with a parameter count limited to just 50KB. Our code is available at https://github.com/JCruan519/EGE-UNet ." @default.
- W4387211614 created "2023-10-01" @default.
- W4387211614 creator A5020776216 @default.
- W4387211614 creator A5026260510 @default.
- W4387211614 creator A5044897858 @default.
- W4387211614 creator A5057382261 @default.
- W4387211614 creator A5076218215 @default.
- W4387211614 date "2023-01-01" @default.
- W4387211614 modified "2023-10-10" @default.
- W4387211614 title "EGE-UNet: An Efficient Group Enhanced UNet for Skin Lesion Segmentation" @default.
- W4387211614 cites W1901129140 @default.
- W4387211614 cites W2884436604 @default.
- W4387211614 cites W2963163009 @default.
- W4387211614 cites W2982083293 @default.
- W4387211614 cites W3042980549 @default.
- W4387211614 cites W3138516171 @default.
- W4387211614 cites W3203497085 @default.
- W4387211614 cites W3203841574 @default.
- W4387211614 cites W3204166336 @default.
- W4387211614 cites W4295934721 @default.
- W4387211614 cites W4313527340 @default.
- W4387211614 doi "https://doi.org/10.1007/978-3-031-43901-8_46" @default.
- W4387211614 hasPublicationYear "2023" @default.
- W4387211614 type Work @default.
- W4387211614 citedByCount "1" @default.
- W4387211614 crossrefType "book-chapter" @default.
- W4387211614 hasAuthorship W4387211614A5020776216 @default.
- W4387211614 hasAuthorship W4387211614A5026260510 @default.
- W4387211614 hasAuthorship W4387211614A5044897858 @default.
- W4387211614 hasAuthorship W4387211614A5057382261 @default.
- W4387211614 hasAuthorship W4387211614A5076218215 @default.
- W4387211614 hasConcept C134306372 @default.
- W4387211614 hasConcept C154945302 @default.
- W4387211614 hasConcept C177264268 @default.
- W4387211614 hasConcept C199360897 @default.
- W4387211614 hasConcept C2776760102 @default.
- W4387211614 hasConcept C33923547 @default.
- W4387211614 hasConcept C41008148 @default.
- W4387211614 hasConcept C60292330 @default.
- W4387211614 hasConcept C89600930 @default.
- W4387211614 hasConceptScore W4387211614C134306372 @default.
- W4387211614 hasConceptScore W4387211614C154945302 @default.
- W4387211614 hasConceptScore W4387211614C177264268 @default.
- W4387211614 hasConceptScore W4387211614C199360897 @default.
- W4387211614 hasConceptScore W4387211614C2776760102 @default.
- W4387211614 hasConceptScore W4387211614C33923547 @default.
- W4387211614 hasConceptScore W4387211614C41008148 @default.
- W4387211614 hasConceptScore W4387211614C60292330 @default.
- W4387211614 hasConceptScore W4387211614C89600930 @default.
- W4387211614 hasLocation W43872116141 @default.
- W4387211614 hasOpenAccess W4387211614 @default.
- W4387211614 hasPrimaryLocation W43872116141 @default.
- W4387211614 hasRelatedWork W144883078 @default.
- W4387211614 hasRelatedWork W2005437358 @default.
- W4387211614 hasRelatedWork W2138214894 @default.
- W4387211614 hasRelatedWork W2358941527 @default.
- W4387211614 hasRelatedWork W2361006516 @default.
- W4387211614 hasRelatedWork W2373724792 @default.
- W4387211614 hasRelatedWork W2517104666 @default.
- W4387211614 hasRelatedWork W2532775738 @default.
- W4387211614 hasRelatedWork W2954384599 @default.
- W4387211614 hasRelatedWork W4385556756 @default.
- W4387211614 isParatext "false" @default.
- W4387211614 isRetracted "false" @default.
- W4387211614 workType "book-chapter" @default.