Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912237114> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2912237114 abstract "Recently, state-of-the-art results have been achieved in semantic segmentation using fully convolutional networks (FCNs). Most of these networks employ encoder-decoder style architecture similar to U-Net and are trained with images and the corresponding segmentation maps as a pixel-wise classification task. Such frameworks only exploit class information by using the ground truth segmentation maps. In this paper, we propose a multi-task learning framework with the main aim of exploiting structural and spatial information along with the class information. We modify the decoder part of the FCN to exploit class information and the structural information as well. We intend to do this while also keeping the parameters of the network as low as possible. We obtain the structural information using either of the two ways: i) using the contour map and ii) using the distance map, both of which can be obtained from ground truth segmentation maps with no additional annotation costs. We also explore different ways in which distance maps can be computed and study the effects of different distance maps on the segmentation performance. We also experiment extensively on two different medical image segmentation applications: i.e i) using color fundus images for optic disc and cup segmentation and ii) using endoscopic images for polyp segmentation. Through our experiments, we report results comparable to, and in some cases performing better than the current state-of-the-art architectures and with an order of 2x reduction in the number of parameters." @default.
- W2912237114 created "2019-02-21" @default.
- W2912237114 creator A5019612513 @default.
- W2912237114 creator A5053612846 @default.
- W2912237114 creator A5056763944 @default.
- W2912237114 creator A5082792887 @default.
- W2912237114 creator A5083037666 @default.
- W2912237114 date "2019-01-25" @default.
- W2912237114 modified "2023-10-16" @default.
- W2912237114 title "Joint shape learning and segmentation for medical images using a minimalistic deep network" @default.
- W2912237114 cites W1901129140 @default.
- W2912237114 cites W1974969377 @default.
- W2912237114 cites W2104095591 @default.
- W2912237114 cites W2121947440 @default.
- W2912237114 cites W2125637308 @default.
- W2912237114 cites W2560328367 @default.
- W2912237114 cites W2564782580 @default.
- W2912237114 cites W2592929672 @default.
- W2912237114 cites W2777186991 @default.
- W2912237114 cites W2806595474 @default.
- W2912237114 cites W2899771611 @default.
- W2912237114 cites W2962914239 @default.
- W2912237114 cites W2963803174 @default.
- W2912237114 cites W3101507774 @default.
- W2912237114 hasPublicationYear "2019" @default.
- W2912237114 type Work @default.
- W2912237114 sameAs 2912237114 @default.
- W2912237114 citedByCount "0" @default.
- W2912237114 crossrefType "posted-content" @default.
- W2912237114 hasAuthorship W2912237114A5019612513 @default.
- W2912237114 hasAuthorship W2912237114A5053612846 @default.
- W2912237114 hasAuthorship W2912237114A5056763944 @default.
- W2912237114 hasAuthorship W2912237114A5082792887 @default.
- W2912237114 hasAuthorship W2912237114A5083037666 @default.
- W2912237114 hasConcept C108583219 @default.
- W2912237114 hasConcept C111919701 @default.
- W2912237114 hasConcept C118487528 @default.
- W2912237114 hasConcept C118505674 @default.
- W2912237114 hasConcept C124504099 @default.
- W2912237114 hasConcept C146849305 @default.
- W2912237114 hasConcept C153180895 @default.
- W2912237114 hasConcept C154945302 @default.
- W2912237114 hasConcept C165696696 @default.
- W2912237114 hasConcept C25694479 @default.
- W2912237114 hasConcept C2776391266 @default.
- W2912237114 hasConcept C31972630 @default.
- W2912237114 hasConcept C38652104 @default.
- W2912237114 hasConcept C41008148 @default.
- W2912237114 hasConcept C65885262 @default.
- W2912237114 hasConcept C71924100 @default.
- W2912237114 hasConcept C89600930 @default.
- W2912237114 hasConceptScore W2912237114C108583219 @default.
- W2912237114 hasConceptScore W2912237114C111919701 @default.
- W2912237114 hasConceptScore W2912237114C118487528 @default.
- W2912237114 hasConceptScore W2912237114C118505674 @default.
- W2912237114 hasConceptScore W2912237114C124504099 @default.
- W2912237114 hasConceptScore W2912237114C146849305 @default.
- W2912237114 hasConceptScore W2912237114C153180895 @default.
- W2912237114 hasConceptScore W2912237114C154945302 @default.
- W2912237114 hasConceptScore W2912237114C165696696 @default.
- W2912237114 hasConceptScore W2912237114C25694479 @default.
- W2912237114 hasConceptScore W2912237114C2776391266 @default.
- W2912237114 hasConceptScore W2912237114C31972630 @default.
- W2912237114 hasConceptScore W2912237114C38652104 @default.
- W2912237114 hasConceptScore W2912237114C41008148 @default.
- W2912237114 hasConceptScore W2912237114C65885262 @default.
- W2912237114 hasConceptScore W2912237114C71924100 @default.
- W2912237114 hasConceptScore W2912237114C89600930 @default.
- W2912237114 hasLocation W29122371141 @default.
- W2912237114 hasOpenAccess W2912237114 @default.
- W2912237114 hasPrimaryLocation W29122371141 @default.
- W2912237114 hasRelatedWork W134390715 @default.
- W2912237114 hasRelatedWork W1541332610 @default.
- W2912237114 hasRelatedWork W16865847 @default.
- W2912237114 hasRelatedWork W2313657968 @default.
- W2912237114 hasRelatedWork W2467119921 @default.
- W2912237114 hasRelatedWork W2530751448 @default.
- W2912237114 hasRelatedWork W2732931556 @default.
- W2912237114 hasRelatedWork W2911584164 @default.
- W2912237114 hasRelatedWork W2943038984 @default.
- W2912237114 hasRelatedWork W2962793336 @default.
- W2912237114 hasRelatedWork W2979600871 @default.
- W2912237114 hasRelatedWork W3089824381 @default.
- W2912237114 hasRelatedWork W3103811167 @default.
- W2912237114 hasRelatedWork W3122184312 @default.
- W2912237114 hasRelatedWork W3126174283 @default.
- W2912237114 hasRelatedWork W3139155446 @default.
- W2912237114 hasRelatedWork W3146991503 @default.
- W2912237114 hasRelatedWork W3175615587 @default.
- W2912237114 hasRelatedWork W3206579576 @default.
- W2912237114 hasRelatedWork W3211857712 @default.
- W2912237114 isParatext "false" @default.
- W2912237114 isRetracted "false" @default.
- W2912237114 magId "2912237114" @default.
- W2912237114 workType "article" @default.