Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387430145> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387430145 endingPage "171" @default.
- W4387430145 startingPage "159" @default.
- W4387430145 abstract "Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at GitHub ." @default.
- W4387430145 created "2023-10-08" @default.
- W4387430145 creator A5008523578 @default.
- W4387430145 creator A5064747056 @default.
- W4387430145 creator A5087512747 @default.
- W4387430145 date "2023-01-01" @default.
- W4387430145 modified "2023-10-09" @default.
- W4387430145 title "Self-supervised Few-Shot Learning for Semantic Segmentation: An Annotation-Free Approach" @default.
- W4387430145 cites W1948751323 @default.
- W4387430145 cites W2061253660 @default.
- W4387430145 cites W2778764040 @default.
- W4387430145 cites W2883725317 @default.
- W4387430145 cites W2963078159 @default.
- W4387430145 cites W2963599420 @default.
- W4387430145 cites W2965729941 @default.
- W4387430145 cites W2990230185 @default.
- W4387430145 cites W2990500698 @default.
- W4387430145 cites W3033502887 @default.
- W4387430145 cites W3047258141 @default.
- W4387430145 cites W3108187451 @default.
- W4387430145 cites W3118439879 @default.
- W4387430145 cites W3193301950 @default.
- W4387430145 cites W3203302137 @default.
- W4387430145 cites W4211186538 @default.
- W4387430145 cites W4214573368 @default.
- W4387430145 cites W4313150877 @default.
- W4387430145 cites W4317425485 @default.
- W4387430145 cites W4319300548 @default.
- W4387430145 cites W4323569058 @default.
- W4387430145 doi "https://doi.org/10.1007/978-3-031-46005-0_14" @default.
- W4387430145 hasPublicationYear "2023" @default.
- W4387430145 type Work @default.
- W4387430145 citedByCount "0" @default.
- W4387430145 crossrefType "book-chapter" @default.
- W4387430145 hasAuthorship W4387430145A5008523578 @default.
- W4387430145 hasAuthorship W4387430145A5064747056 @default.
- W4387430145 hasAuthorship W4387430145A5087512747 @default.
- W4387430145 hasConcept C115961682 @default.
- W4387430145 hasConcept C119857082 @default.
- W4387430145 hasConcept C124504099 @default.
- W4387430145 hasConcept C132525143 @default.
- W4387430145 hasConcept C153180895 @default.
- W4387430145 hasConcept C154945302 @default.
- W4387430145 hasConcept C1667742 @default.
- W4387430145 hasConcept C199579030 @default.
- W4387430145 hasConcept C2776321320 @default.
- W4387430145 hasConcept C41008148 @default.
- W4387430145 hasConcept C80444323 @default.
- W4387430145 hasConcept C89600930 @default.
- W4387430145 hasConceptScore W4387430145C115961682 @default.
- W4387430145 hasConceptScore W4387430145C119857082 @default.
- W4387430145 hasConceptScore W4387430145C124504099 @default.
- W4387430145 hasConceptScore W4387430145C132525143 @default.
- W4387430145 hasConceptScore W4387430145C153180895 @default.
- W4387430145 hasConceptScore W4387430145C154945302 @default.
- W4387430145 hasConceptScore W4387430145C1667742 @default.
- W4387430145 hasConceptScore W4387430145C199579030 @default.
- W4387430145 hasConceptScore W4387430145C2776321320 @default.
- W4387430145 hasConceptScore W4387430145C41008148 @default.
- W4387430145 hasConceptScore W4387430145C80444323 @default.
- W4387430145 hasConceptScore W4387430145C89600930 @default.
- W4387430145 hasLocation W43874301451 @default.
- W4387430145 hasOpenAccess W4387430145 @default.
- W4387430145 hasPrimaryLocation W43874301451 @default.
- W4387430145 hasRelatedWork W2052697133 @default.
- W4387430145 hasRelatedWork W2076896210 @default.
- W4387430145 hasRelatedWork W2093596879 @default.
- W4387430145 hasRelatedWork W2117928543 @default.
- W4387430145 hasRelatedWork W2119028572 @default.
- W4387430145 hasRelatedWork W2152482390 @default.
- W4387430145 hasRelatedWork W2365617273 @default.
- W4387430145 hasRelatedWork W2376984068 @default.
- W4387430145 hasRelatedWork W2384288472 @default.
- W4387430145 hasRelatedWork W3177930984 @default.
- W4387430145 isParatext "false" @default.
- W4387430145 isRetracted "false" @default.
- W4387430145 workType "book-chapter" @default.