Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091601247> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3091601247 abstract "Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this paper, we present a data efficient learning framework using the recent concept of Generative Adversarial Networks; this allows a deep neural network to perform significantly better than its fully supervised counterpart in low annotation regime. The proposed method is an extension of our previous work with the addition of a new unsupervised adversarial loss and a structured prediction based architecture. Though generic, we demonstrate the efficacy of our approach for retinal blood vessels segmentation from fundus images on DRIVE and STARE datasets. We experiment with extreme low annotation budget and we show, that under this constrained data setting, the proposed method outperforms our previous method and other fully supervised benchmark models. In addition, our systematic ablation studies suggest some key observations for successfully training GAN based semi-supervised algorithms with an encoder-decoder style network architecture." @default.
- W3091601247 created "2020-10-08" @default.
- W3091601247 creator A5004059019 @default.
- W3091601247 creator A5018868625 @default.
- W3091601247 creator A5045635774 @default.
- W3091601247 creator A5082039339 @default.
- W3091601247 date "2020-10-01" @default.
- W3091601247 modified "2023-09-30" @default.
- W3091601247 title "Retinal Vessel Segmentation Under Extreme Low Annotation: A Gan Based Semi-Supervised Approach" @default.
- W3091601247 cites W2010965043 @default.
- W3091601247 cites W2037776979 @default.
- W3091601247 cites W2063603043 @default.
- W3091601247 cites W2109037308 @default.
- W3091601247 cites W2116628223 @default.
- W3091601247 cites W2141708418 @default.
- W3091601247 cites W2150769593 @default.
- W3091601247 cites W2163344010 @default.
- W3091601247 cites W2266464013 @default.
- W3091601247 cites W2327793514 @default.
- W3091601247 cites W2527341761 @default.
- W3091601247 cites W2556022279 @default.
- W3091601247 cites W2572730214 @default.
- W3091601247 cites W2693096534 @default.
- W3091601247 cites W2736462652 @default.
- W3091601247 cites W3098547059 @default.
- W3091601247 cites W3105842011 @default.
- W3091601247 doi "https://doi.org/10.1109/icip40778.2020.9190882" @default.
- W3091601247 hasPublicationYear "2020" @default.
- W3091601247 type Work @default.
- W3091601247 sameAs 3091601247 @default.
- W3091601247 citedByCount "11" @default.
- W3091601247 countsByYear W30916012472021 @default.
- W3091601247 countsByYear W30916012472022 @default.
- W3091601247 countsByYear W30916012472023 @default.
- W3091601247 crossrefType "proceedings-article" @default.
- W3091601247 hasAuthorship W3091601247A5004059019 @default.
- W3091601247 hasAuthorship W3091601247A5018868625 @default.
- W3091601247 hasAuthorship W3091601247A5045635774 @default.
- W3091601247 hasAuthorship W3091601247A5082039339 @default.
- W3091601247 hasConcept C124504099 @default.
- W3091601247 hasConcept C153180895 @default.
- W3091601247 hasConcept C154945302 @default.
- W3091601247 hasConcept C204321447 @default.
- W3091601247 hasConcept C2776321320 @default.
- W3091601247 hasConcept C31972630 @default.
- W3091601247 hasConcept C41008148 @default.
- W3091601247 hasConcept C89600930 @default.
- W3091601247 hasConceptScore W3091601247C124504099 @default.
- W3091601247 hasConceptScore W3091601247C153180895 @default.
- W3091601247 hasConceptScore W3091601247C154945302 @default.
- W3091601247 hasConceptScore W3091601247C204321447 @default.
- W3091601247 hasConceptScore W3091601247C2776321320 @default.
- W3091601247 hasConceptScore W3091601247C31972630 @default.
- W3091601247 hasConceptScore W3091601247C41008148 @default.
- W3091601247 hasConceptScore W3091601247C89600930 @default.
- W3091601247 hasLocation W30916012471 @default.
- W3091601247 hasOpenAccess W3091601247 @default.
- W3091601247 hasPrimaryLocation W30916012471 @default.
- W3091601247 hasRelatedWork W1669643531 @default.
- W3091601247 hasRelatedWork W1700740617 @default.
- W3091601247 hasRelatedWork W1721780360 @default.
- W3091601247 hasRelatedWork W2110230079 @default.
- W3091601247 hasRelatedWork W2117664411 @default.
- W3091601247 hasRelatedWork W2117933325 @default.
- W3091601247 hasRelatedWork W2122581818 @default.
- W3091601247 hasRelatedWork W2159066190 @default.
- W3091601247 hasRelatedWork W2739874619 @default.
- W3091601247 hasRelatedWork W1967061043 @default.
- W3091601247 isParatext "false" @default.
- W3091601247 isRetracted "false" @default.
- W3091601247 magId "3091601247" @default.
- W3091601247 workType "article" @default.