Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387560100> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387560100 abstract "Polyp segmentation is crucial for preventing colorectal cancer a common type of cancer. Deep learning has been used to segment polyps automatically, which reduces the risk of misdiagnosis. Localizing small polyps in colonoscopy images is challenging because of its complex characteristics, such as color, occlusion, and various shapes of polyps. To address this challenge, a novel frequency-based fully convolutional neural network, Multi-Frequency Feature Fusion Polyp Segmentation Network (M3FPolypSegNet) was proposed to decompose the input image into low/high/full-frequency components to use the characteristics of each component. We used three independent multi-frequency encoders to map multiple input images into a high-dimensional feature space. In the Frequency-ASPP Scalable Attention Module (F-ASPP SAM), ASPP was applied between each frequency component to preserve scale information. Subsequently, scalable attention was applied to emphasize polyp regions in a high-dimensional feature space. Finally, we designed three multi-task learning (i.e., region, edge, and distance) in four decoder blocks to learn the structural characteristics of the region. The proposed model outperformed various segmentation models with performance gains of 6.92% and 7.52% on average for all metrics on CVC-ClinicDB and BKAI-IGH-NeoPolyp, respectively." @default.
- W4387560100 created "2023-10-12" @default.
- W4387560100 creator A5020456546 @default.
- W4387560100 creator A5032958224 @default.
- W4387560100 creator A5036806967 @default.
- W4387560100 creator A5072405403 @default.
- W4387560100 creator A5073820638 @default.
- W4387560100 creator A5081113412 @default.
- W4387560100 date "2023-10-09" @default.
- W4387560100 modified "2023-10-13" @default.
- W4387560100 title "M3FPolypSegNet: Segmentation Network with Multi-frequency Feature Fusion for Polyp Localization in Colonoscopy Images" @default.
- W4387560100 doi "https://doi.org/10.48550/arxiv.2310.05538" @default.
- W4387560100 hasPublicationYear "2023" @default.
- W4387560100 type Work @default.
- W4387560100 citedByCount "0" @default.
- W4387560100 crossrefType "posted-content" @default.
- W4387560100 hasAuthorship W4387560100A5020456546 @default.
- W4387560100 hasAuthorship W4387560100A5032958224 @default.
- W4387560100 hasAuthorship W4387560100A5036806967 @default.
- W4387560100 hasAuthorship W4387560100A5072405403 @default.
- W4387560100 hasAuthorship W4387560100A5073820638 @default.
- W4387560100 hasAuthorship W4387560100A5081113412 @default.
- W4387560100 hasBestOaLocation W43875601001 @default.
- W4387560100 hasConcept C100921725 @default.
- W4387560100 hasConcept C108583219 @default.
- W4387560100 hasConcept C111919701 @default.
- W4387560100 hasConcept C118505674 @default.
- W4387560100 hasConcept C120665830 @default.
- W4387560100 hasConcept C121332964 @default.
- W4387560100 hasConcept C138885662 @default.
- W4387560100 hasConcept C153180895 @default.
- W4387560100 hasConcept C154945302 @default.
- W4387560100 hasConcept C168167062 @default.
- W4387560100 hasConcept C2776401178 @default.
- W4387560100 hasConcept C31972630 @default.
- W4387560100 hasConcept C41008148 @default.
- W4387560100 hasConcept C41895202 @default.
- W4387560100 hasConcept C48044578 @default.
- W4387560100 hasConcept C77088390 @default.
- W4387560100 hasConcept C81363708 @default.
- W4387560100 hasConcept C83665646 @default.
- W4387560100 hasConcept C89600930 @default.
- W4387560100 hasConcept C97355855 @default.
- W4387560100 hasConceptScore W4387560100C100921725 @default.
- W4387560100 hasConceptScore W4387560100C108583219 @default.
- W4387560100 hasConceptScore W4387560100C111919701 @default.
- W4387560100 hasConceptScore W4387560100C118505674 @default.
- W4387560100 hasConceptScore W4387560100C120665830 @default.
- W4387560100 hasConceptScore W4387560100C121332964 @default.
- W4387560100 hasConceptScore W4387560100C138885662 @default.
- W4387560100 hasConceptScore W4387560100C153180895 @default.
- W4387560100 hasConceptScore W4387560100C154945302 @default.
- W4387560100 hasConceptScore W4387560100C168167062 @default.
- W4387560100 hasConceptScore W4387560100C2776401178 @default.
- W4387560100 hasConceptScore W4387560100C31972630 @default.
- W4387560100 hasConceptScore W4387560100C41008148 @default.
- W4387560100 hasConceptScore W4387560100C41895202 @default.
- W4387560100 hasConceptScore W4387560100C48044578 @default.
- W4387560100 hasConceptScore W4387560100C77088390 @default.
- W4387560100 hasConceptScore W4387560100C81363708 @default.
- W4387560100 hasConceptScore W4387560100C83665646 @default.
- W4387560100 hasConceptScore W4387560100C89600930 @default.
- W4387560100 hasConceptScore W4387560100C97355855 @default.
- W4387560100 hasLocation W43875601001 @default.
- W4387560100 hasOpenAccess W4387560100 @default.
- W4387560100 hasPrimaryLocation W43875601001 @default.
- W4387560100 hasRelatedWork W1838576100 @default.
- W4387560100 hasRelatedWork W1983399550 @default.
- W4387560100 hasRelatedWork W2089704382 @default.
- W4387560100 hasRelatedWork W2095886385 @default.
- W4387560100 hasRelatedWork W2384362569 @default.
- W4387560100 hasRelatedWork W2389214306 @default.
- W4387560100 hasRelatedWork W2965083567 @default.
- W4387560100 hasRelatedWork W4235240664 @default.
- W4387560100 hasRelatedWork W4293226380 @default.
- W4387560100 hasRelatedWork W2181948922 @default.
- W4387560100 isParatext "false" @default.
- W4387560100 isRetracted "false" @default.
- W4387560100 workType "article" @default.