Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380136691> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4380136691 abstract "Deep learning-based medical image segmentation models suffer from performance degradation when deployed to a new healthcare center. To address this issue, unsupervised domain adaptation and multi-source domain generalization methods have been proposed, which, however, are less favorable for clinical practice due to the cost of acquiring target-domain data and the privacy concerns associated with redistributing the data from multiple source domains. In this paper, we propose a textbf{C}hannel-level textbf{C}ontrastive textbf{S}ingle textbf{D}omain textbf{G}eneralization (textbf{C$^2$SDG}) model for medical image segmentation. In C$^2$SDG, the shallower features of each image and its style-augmented counterpart are extracted and used for contrastive training, resulting in the disentangled style representations and structure representations. The segmentation is performed based solely on the structure representations. Our method is novel in the contrastive perspective that enables channel-wise feature disentanglement using a single source domain. We evaluated C$^2$SDG against six SDG methods on a multi-domain joint optic cup and optic disc segmentation benchmark. Our results suggest the effectiveness of each module in C$^2$SDG and also indicate that C$^2$SDG outperforms the baseline and all competing methods with a large margin. The code will be available at url{https://github.com/ShishuaiHu/CCSDG}." @default.
- W4380136691 created "2023-06-10" @default.
- W4380136691 creator A5034520275 @default.
- W4380136691 creator A5045416617 @default.
- W4380136691 creator A5083195196 @default.
- W4380136691 date "2023-06-08" @default.
- W4380136691 modified "2023-09-24" @default.
- W4380136691 title "Devil is in Channels: Contrastive Single Domain Generalization for Medical Image Segmentation" @default.
- W4380136691 doi "https://doi.org/10.48550/arxiv.2306.05254" @default.
- W4380136691 hasPublicationYear "2023" @default.
- W4380136691 type Work @default.
- W4380136691 citedByCount "0" @default.
- W4380136691 crossrefType "posted-content" @default.
- W4380136691 hasAuthorship W4380136691A5034520275 @default.
- W4380136691 hasAuthorship W4380136691A5045416617 @default.
- W4380136691 hasAuthorship W4380136691A5083195196 @default.
- W4380136691 hasBestOaLocation W43801366911 @default.
- W4380136691 hasConcept C115961682 @default.
- W4380136691 hasConcept C119857082 @default.
- W4380136691 hasConcept C13280743 @default.
- W4380136691 hasConcept C134306372 @default.
- W4380136691 hasConcept C138885662 @default.
- W4380136691 hasConcept C153180895 @default.
- W4380136691 hasConcept C154945302 @default.
- W4380136691 hasConcept C177148314 @default.
- W4380136691 hasConcept C177264268 @default.
- W4380136691 hasConcept C185798385 @default.
- W4380136691 hasConcept C199360897 @default.
- W4380136691 hasConcept C205649164 @default.
- W4380136691 hasConcept C2776401178 @default.
- W4380136691 hasConcept C2776760102 @default.
- W4380136691 hasConcept C33923547 @default.
- W4380136691 hasConcept C36503486 @default.
- W4380136691 hasConcept C41008148 @default.
- W4380136691 hasConcept C41895202 @default.
- W4380136691 hasConcept C774472 @default.
- W4380136691 hasConcept C89600930 @default.
- W4380136691 hasConceptScore W4380136691C115961682 @default.
- W4380136691 hasConceptScore W4380136691C119857082 @default.
- W4380136691 hasConceptScore W4380136691C13280743 @default.
- W4380136691 hasConceptScore W4380136691C134306372 @default.
- W4380136691 hasConceptScore W4380136691C138885662 @default.
- W4380136691 hasConceptScore W4380136691C153180895 @default.
- W4380136691 hasConceptScore W4380136691C154945302 @default.
- W4380136691 hasConceptScore W4380136691C177148314 @default.
- W4380136691 hasConceptScore W4380136691C177264268 @default.
- W4380136691 hasConceptScore W4380136691C185798385 @default.
- W4380136691 hasConceptScore W4380136691C199360897 @default.
- W4380136691 hasConceptScore W4380136691C205649164 @default.
- W4380136691 hasConceptScore W4380136691C2776401178 @default.
- W4380136691 hasConceptScore W4380136691C2776760102 @default.
- W4380136691 hasConceptScore W4380136691C33923547 @default.
- W4380136691 hasConceptScore W4380136691C36503486 @default.
- W4380136691 hasConceptScore W4380136691C41008148 @default.
- W4380136691 hasConceptScore W4380136691C41895202 @default.
- W4380136691 hasConceptScore W4380136691C774472 @default.
- W4380136691 hasConceptScore W4380136691C89600930 @default.
- W4380136691 hasLocation W43801366911 @default.
- W4380136691 hasOpenAccess W4380136691 @default.
- W4380136691 hasPrimaryLocation W43801366911 @default.
- W4380136691 hasRelatedWork W2148443709 @default.
- W4380136691 hasRelatedWork W2213006595 @default.
- W4380136691 hasRelatedWork W2319888919 @default.
- W4380136691 hasRelatedWork W2517490240 @default.
- W4380136691 hasRelatedWork W2532775738 @default.
- W4380136691 hasRelatedWork W2772065891 @default.
- W4380136691 hasRelatedWork W2952094804 @default.
- W4380136691 hasRelatedWork W4206076898 @default.
- W4380136691 hasRelatedWork W4225747855 @default.
- W4380136691 hasRelatedWork W4298482256 @default.
- W4380136691 isParatext "false" @default.
- W4380136691 isRetracted "false" @default.
- W4380136691 workType "article" @default.