Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204163667> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3204163667 endingPage "281" @default.
- W3204163667 startingPage "272" @default.
- W3204163667 abstract "Surgical instrument segmentation is fundamental for the advanced computer-assisted system. The variability of the surgical scene, a major obstacle in this task, leads to the domain shift problem. Unsupervised domain adaptation (UDA) technique can be employed to solve this problem and adapt the model to various surgical scenarios. However, existing UDA methods ignore the relationship among different categories, hindering the model learning discriminative features from a global view. Additionally, the adversarial strategy utilized in these methods only narrows down the domain gap at the end of the network, leading to the poor feature alignment. To tackle above mentioned problems, we advance a semantic-prototype interaction graph (SePIG) framework for surgical instrument type segmentation to grasp the category-level relationship and further align the feature distribution. The proposed framework consists of prototypical inner-interaction graph (PI-Graph) and prototypical cross-interaction graph (PC-Graph). In PI-Graph, EM-Grouping module is designed to generate multi-prototypes representing the semantic information adequately. Then, propagation is performed upon these multi-prototypes to communicate semantic information inner each domain. Aiming at narrowing down the domain gaps, the PC-Graph constructs hierarchical graphs upon multi-prototypes and category centers, and conducts dynamic reasoning to exchange the correlated information among two domains. Extensive experiments on the EndoVis Instrument Segmentation 2017 (rightarrow ) 2018 scenarios demonstrate the superiority of our SePIG framework compared with state-of-the-art methods. Code is available at https://github.com/CityU-AIM-Group/SePIG." @default.
- W3204163667 created "2021-10-11" @default.
- W3204163667 creator A5041019033 @default.
- W3204163667 creator A5059247334 @default.
- W3204163667 creator A5073968803 @default.
- W3204163667 date "2021-01-01" @default.
- W3204163667 modified "2023-10-06" @default.
- W3204163667 title "Prototypical Interaction Graph for Unsupervised Domain Adaptation in Surgical Instrument Segmentation" @default.
- W3204163667 cites W1985690171 @default.
- W3204163667 cites W2604690505 @default.
- W3204163667 cites W2753115354 @default.
- W3204163667 cites W2895281799 @default.
- W3204163667 cites W2950111065 @default.
- W3204163667 cites W2962685880 @default.
- W3204163667 cites W2963107255 @default.
- W3204163667 cites W2969893028 @default.
- W3204163667 cites W2979801810 @default.
- W3204163667 cites W2979922443 @default.
- W3204163667 cites W2981462961 @default.
- W3204163667 cites W2990230185 @default.
- W3204163667 cites W2990775046 @default.
- W3204163667 cites W2991559096 @default.
- W3204163667 cites W3034417116 @default.
- W3204163667 cites W3035294798 @default.
- W3204163667 cites W3096104140 @default.
- W3204163667 cites W3096667748 @default.
- W3204163667 cites W3101468328 @default.
- W3204163667 doi "https://doi.org/10.1007/978-3-030-87199-4_26" @default.
- W3204163667 hasPublicationYear "2021" @default.
- W3204163667 type Work @default.
- W3204163667 sameAs 3204163667 @default.
- W3204163667 citedByCount "6" @default.
- W3204163667 countsByYear W32041636672023 @default.
- W3204163667 crossrefType "book-chapter" @default.
- W3204163667 hasAuthorship W3204163667A5041019033 @default.
- W3204163667 hasAuthorship W3204163667A5059247334 @default.
- W3204163667 hasAuthorship W3204163667A5073968803 @default.
- W3204163667 hasConcept C119857082 @default.
- W3204163667 hasConcept C132525143 @default.
- W3204163667 hasConcept C134306372 @default.
- W3204163667 hasConcept C138885662 @default.
- W3204163667 hasConcept C153180895 @default.
- W3204163667 hasConcept C154945302 @default.
- W3204163667 hasConcept C2776401178 @default.
- W3204163667 hasConcept C33923547 @default.
- W3204163667 hasConcept C36503486 @default.
- W3204163667 hasConcept C41008148 @default.
- W3204163667 hasConcept C41895202 @default.
- W3204163667 hasConcept C80444323 @default.
- W3204163667 hasConcept C89600930 @default.
- W3204163667 hasConcept C97931131 @default.
- W3204163667 hasConceptScore W3204163667C119857082 @default.
- W3204163667 hasConceptScore W3204163667C132525143 @default.
- W3204163667 hasConceptScore W3204163667C134306372 @default.
- W3204163667 hasConceptScore W3204163667C138885662 @default.
- W3204163667 hasConceptScore W3204163667C153180895 @default.
- W3204163667 hasConceptScore W3204163667C154945302 @default.
- W3204163667 hasConceptScore W3204163667C2776401178 @default.
- W3204163667 hasConceptScore W3204163667C33923547 @default.
- W3204163667 hasConceptScore W3204163667C36503486 @default.
- W3204163667 hasConceptScore W3204163667C41008148 @default.
- W3204163667 hasConceptScore W3204163667C41895202 @default.
- W3204163667 hasConceptScore W3204163667C80444323 @default.
- W3204163667 hasConceptScore W3204163667C89600930 @default.
- W3204163667 hasConceptScore W3204163667C97931131 @default.
- W3204163667 hasLocation W32041636671 @default.
- W3204163667 hasOpenAccess W3204163667 @default.
- W3204163667 hasPrimaryLocation W32041636671 @default.
- W3204163667 hasRelatedWork W1972656095 @default.
- W3204163667 hasRelatedWork W2024160000 @default.
- W3204163667 hasRelatedWork W2061273563 @default.
- W3204163667 hasRelatedWork W2285052147 @default.
- W3204163667 hasRelatedWork W2729514902 @default.
- W3204163667 hasRelatedWork W2743258233 @default.
- W3204163667 hasRelatedWork W2773500201 @default.
- W3204163667 hasRelatedWork W2970216048 @default.
- W3204163667 hasRelatedWork W2998168123 @default.
- W3204163667 hasRelatedWork W4287995534 @default.
- W3204163667 isParatext "false" @default.
- W3204163667 isRetracted "false" @default.
- W3204163667 magId "3204163667" @default.
- W3204163667 workType "book-chapter" @default.