FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226304999> ?p ?o ?g. }

• W4226304999 endingPage "2597" @default.
• W4226304999 startingPage "2582" @default.
• W4226304999 abstract "Deep learning (DL) based semantic segmentation methods have achieved excellent performance in biomedical image segmentation, producing high quality probability maps to allow extraction of rich instance information to facilitate good instance segmentation. While numerous efforts were put into developing new DL semantic segmentation models, less attention was paid to a key issue of how to effectively explore their probability maps to attain the best possible instance segmentation. We observe that probability maps by DL semantic segmentation models can be used to generate many possible instance candidates, and accurate instance segmentation can be achieved by selecting from them a set of optimized candidates as output instances. Further, the generated instance candidates form a well-behaved hierarchical structure (a forest), which allows selecting instances in an optimized manner. Hence, we propose a novel framework, called hierarchical earth mover's distance (H-EMD), for instance segmentation in biomedical 2D+time videos and 3D images, which judiciously incorporates consistent instance selection with semantic-segmentation-generated probability maps. H-EMD contains two main stages: (1) instance candidate generation: capturing instance-structured information in probability maps by generating many instance candidates in a forest structure; (2) instance candidate selection: selecting instances from the candidate set for final instance segmentation. We formulate a key instance selection problem on the instance candidate forest as an optimization problem based on the earth mover's distance (EMD), and solve it by integer linear programming. Extensive experiments on eight biomedical video or 3D datasets demonstrate that H-EMD consistently boosts DL semantic segmentation models and is highly competitive with state-of-the-art methods." @default.
• W4226304999 created "2022-05-05" @default.
• W4226304999 creator A5051836187 @default.
• W4226304999 creator A5052870302 @default.
• W4226304999 creator A5060901632 @default.
• W4226304999 creator A5062012269 @default.
• W4226304999 creator A5069345995 @default.
• W4226304999 creator A5080704847 @default.
• W4226304999 creator A5081872106 @default.
• W4226304999 creator A5084597959 @default.
• W4226304999 date "2022-10-01" @default.
• W4226304999 modified "2023-09-30" @default.
• W4226304999 title "H-EMD: A Hierarchical Earth Mover’s Distance Method for Instance Segmentation" @default.
• W4226304999 cites W130423592 @default.
• W4226304999 cites W1966828720 @default.
• W4226304999 cites W1973884997 @default.
• W4226304999 cites W2025818287 @default.
• W4226304999 cites W2047076586 @default.
• W4226304999 cites W2067191022 @default.
• W4226304999 cites W2075564365 @default.
• W4226304999 cites W2103243046 @default.
• W4226304999 cites W2125101937 @default.
• W4226304999 cites W2129223507 @default.
• W4226304999 cites W2133059825 @default.
• W4226304999 cites W2141273399 @default.
• W4226304999 cites W2142532592 @default.
• W4226304999 cites W2301358467 @default.
• W4226304999 cites W2313683793 @default.
• W4226304999 cites W2328617829 @default.
• W4226304999 cites W2424374314 @default.
• W4226304999 cites W2439117641 @default.
• W4226304999 cites W2557889580 @default.
• W4226304999 cites W2562612963 @default.
• W4226304999 cites W2574209618 @default.
• W4226304999 cites W2758694956 @default.
• W4226304999 cites W2767353193 @default.
• W4226304999 cites W2805735218 @default.
• W4226304999 cites W2806190463 @default.
• W4226304999 cites W2806581075 @default.
• W4226304999 cites W2885343725 @default.
• W4226304999 cites W2911810446 @default.
• W4226304999 cites W2914162368 @default.
• W4226304999 cites W2916797271 @default.
• W4226304999 cites W2921092847 @default.
• W4226304999 cites W2945333368 @default.
• W4226304999 cites W2955521425 @default.
• W4226304999 cites W2963150697 @default.
• W4226304999 cites W2963454900 @default.
• W4226304999 cites W2963574983 @default.
• W4226304999 cites W2963609467 @default.
• W4226304999 cites W2963659353 @default.
• W4226304999 cites W2963803174 @default.
• W4226304999 cites W2963869116 @default.
• W4226304999 cites W2974825848 @default.
• W4226304999 cites W2980134246 @default.
• W4226304999 cites W2980199518 @default.
• W4226304999 cites W3034351081 @default.
• W4226304999 cites W3100296314 @default.
• W4226304999 cites W3111521801 @default.
• W4226304999 cites W3112701542 @default.
• W4226304999 cites W3113410735 @default.
• W4226304999 cites W3142772534 @default.
• W4226304999 cites W3186741760 @default.
• W4226304999 cites W4205089880 @default.
• W4226304999 cites W4205690532 @default.
• W4226304999 doi "https://doi.org/10.1109/tmi.2022.3169449" @default.
• W4226304999 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35446762" @default.
• W4226304999 hasPublicationYear "2022" @default.
• W4226304999 type Work @default.
• W4226304999 citedByCount "3" @default.
• W4226304999 countsByYear W42263049992022 @default.
• W4226304999 countsByYear W42263049992023 @default.
• W4226304999 crossrefType "journal-article" @default.
• W4226304999 hasAuthorship W4226304999A5051836187 @default.
• W4226304999 hasAuthorship W4226304999A5052870302 @default.
• W4226304999 hasAuthorship W4226304999A5060901632 @default.
• W4226304999 hasAuthorship W4226304999A5062012269 @default.
• W4226304999 hasAuthorship W4226304999A5069345995 @default.
• W4226304999 hasAuthorship W4226304999A5080704847 @default.
• W4226304999 hasAuthorship W4226304999A5081872106 @default.
• W4226304999 hasAuthorship W4226304999A5084597959 @default.
• W4226304999 hasBestOaLocation W42263049992 @default.
• W4226304999 hasConcept C124504099 @default.
• W4226304999 hasConcept C153180895 @default.
• W4226304999 hasConcept C154945302 @default.
• W4226304999 hasConcept C177264268 @default.
• W4226304999 hasConcept C199360897 @default.
• W4226304999 hasConcept C25694479 @default.
• W4226304999 hasConcept C41008148 @default.
• W4226304999 hasConcept C65885262 @default.
• W4226304999 hasConcept C81917197 @default.
• W4226304999 hasConcept C82668687 @default.
• W4226304999 hasConcept C89600930 @default.
• W4226304999 hasConceptScore W4226304999C124504099 @default.
• W4226304999 hasConceptScore W4226304999C153180895 @default.
• W4226304999 hasConceptScore W4226304999C154945302 @default.
• W4226304999 hasConceptScore W4226304999C177264268 @default.
• W4226304999 hasConceptScore W4226304999C199360897 @default.

• next