FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083722602> ?p ?o ?g. }

• W3083722602 abstract "The segmentation of the retinal vasculature from eye fundus images represents one of the most fundamental tasks in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. Specifically, we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. In addition, we propose a simple extension, dubbed W-Net, which reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published approach. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation problem is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that allows us to moderately enhance cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we also test our approach on the Artery/Vein segmentation problem, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity in recent literature. All the code to reproduce the results in this paper is released." @default.
• W3083722602 created "2020-09-11" @default.
• W3083722602 creator A5004770604 @default.
• W3083722602 creator A5018407518 @default.
• W3083722602 creator A5044829575 @default.
• W3083722602 creator A5053292735 @default.
• W3083722602 creator A5062952314 @default.
• W3083722602 creator A5064644687 @default.
• W3083722602 date "2020-09-03" @default.
• W3083722602 modified "2023-09-26" @default.
• W3083722602 title "The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models" @default.
• W3083722602 cites W1901129140 @default.
• W3083722602 cites W1924902684 @default.
• W3083722602 cites W1971463309 @default.
• W3083722602 cites W2033723371 @default.
• W3083722602 cites W2051578148 @default.
• W3083722602 cites W2051583891 @default.
• W3083722602 cites W2053782453 @default.
• W3083722602 cites W2105685332 @default.
• W3083722602 cites W2109037308 @default.
• W3083722602 cites W2129098176 @default.
• W3083722602 cites W2129534965 @default.
• W3083722602 cites W2137055403 @default.
• W3083722602 cites W2145305441 @default.
• W3083722602 cites W2150769593 @default.
• W3083722602 cites W2163344010 @default.
• W3083722602 cites W2170092083 @default.
• W3083722602 cites W2171522051 @default.
• W3083722602 cites W2174711832 @default.
• W3083722602 cites W2263861417 @default.
• W3083722602 cites W2320230300 @default.
• W3083722602 cites W2327793514 @default.
• W3083722602 cites W2488605601 @default.
• W3083722602 cites W2527341761 @default.
• W3083722602 cites W2528556198 @default.
• W3083722602 cites W2544277621 @default.
• W3083722602 cites W2573296565 @default.
• W3083722602 cites W2587235033 @default.
• W3083722602 cites W2761299546 @default.
• W3083722602 cites W2783015573 @default.
• W3083722602 cites W2791338647 @default.
• W3083722602 cites W2802388893 @default.
• W3083722602 cites W2804426658 @default.
• W3083722602 cites W2809144587 @default.
• W3083722602 cites W2884292375 @default.
• W3083722602 cites W2891656998 @default.
• W3083722602 cites W2893691907 @default.
• W3083722602 cites W2895693960 @default.
• W3083722602 cites W2902329146 @default.
• W3083722602 cites W2953372035 @default.
• W3083722602 cites W2954246610 @default.
• W3083722602 cites W2955184057 @default.
• W3083722602 cites W2962189327 @default.
• W3083722602 cites W2963163009 @default.
• W3083722602 cites W2963741406 @default.
• W3083722602 cites W2965167740 @default.
• W3083722602 cites W2971614929 @default.
• W3083722602 cites W2976384268 @default.
• W3083722602 cites W2979474465 @default.
• W3083722602 cites W2979509742 @default.
• W3083722602 cites W2979605896 @default.
• W3083722602 cites W2980524126 @default.
• W3083722602 cites W2982364173 @default.
• W3083722602 cites W2999309192 @default.
• W3083722602 cites W3011927872 @default.
• W3083722602 cites W3012840190 @default.
• W3083722602 cites W3014785587 @default.
• W3083722602 cites W3027519656 @default.
• W3083722602 cites W3031997074 @default.
• W3083722602 cites W3048209253 @default.
• W3083722602 cites W3098547059 @default.
• W3083722602 cites W3103835616 @default.
• W3083722602 hasPublicationYear "2020" @default.
• W3083722602 type Work @default.
• W3083722602 sameAs 3083722602 @default.
• W3083722602 citedByCount "3" @default.
• W3083722602 countsByYear W30837226022021 @default.
• W3083722602 crossrefType "posted-content" @default.
• W3083722602 hasAuthorship W3083722602A5004770604 @default.
• W3083722602 hasAuthorship W3083722602A5018407518 @default.
• W3083722602 hasAuthorship W3083722602A5044829575 @default.
• W3083722602 hasAuthorship W3083722602A5053292735 @default.
• W3083722602 hasAuthorship W3083722602A5062952314 @default.
• W3083722602 hasAuthorship W3083722602A5064644687 @default.
• W3083722602 hasConcept C11413529 @default.
• W3083722602 hasConcept C119857082 @default.
• W3083722602 hasConcept C120665830 @default.
• W3083722602 hasConcept C121332964 @default.
• W3083722602 hasConcept C13280743 @default.
• W3083722602 hasConcept C134306372 @default.
• W3083722602 hasConcept C139807058 @default.
• W3083722602 hasConcept C151730666 @default.
• W3083722602 hasConcept C153180895 @default.
• W3083722602 hasConcept C154945302 @default.
• W3083722602 hasConcept C162324750 @default.
• W3083722602 hasConcept C185798385 @default.
• W3083722602 hasConcept C187736073 @default.
• W3083722602 hasConcept C205649164 @default.
• W3083722602 hasConcept C2779343474 @default.
• W3083722602 hasConcept C2780451532 @default.

• next