FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386725051> ?p ?o ?g. }

• W4386725051 endingPage "102958" @default.
• W4386725051 startingPage "102958" @default.
• W4386725051 abstract "The performance of learning-based algorithms improves with the amount of labelled data used for training. Yet, manually annotating data is particularly difficult for medical image segmentation tasks because of the limited expert availability and intensive manual effort required. To reduce manual labelling, active learning (AL) targets the most informative samples from the unlabelled set to annotate and add to the labelled training set. On the one hand, most active learning works have focused on the classification or limited segmentation of natural images, despite active learning being highly desirable in the difficult task of medical image segmentation. On the other hand, uncertainty-based AL approaches notoriously offer sub-optimal batch-query strategies, while diversity-based methods tend to be computationally expensive. Over and above methodological hurdles, random sampling has proven an extremely difficult baseline to outperform when varying learning and sampling conditions. This work aims to take advantage of the diversity and speed offered by random sampling to improve the selection of uncertainty-based AL methods for segmenting medical images. More specifically, we propose to compute uncertainty at the level of batches instead of samples through an original use of stochastic batches (SB) during sampling in AL. Stochastic batch querying is a simple and effective add-on that can be used on top of any uncertainty-based metric. Extensive experiments on two medical image segmentation datasets show that our strategy consistently improves conventional uncertainty-based sampling methods. Our method can hence act as a strong baseline for medical image segmentation. The code is available on: https://github.com/Minimel/StochasticBatchAL.git." @default.
• W4386725051 created "2023-09-15" @default.
• W4386725051 creator A5017608284 @default.
• W4386725051 creator A5048401036 @default.
• W4386725051 creator A5064644687 @default.
• W4386725051 date "2023-12-01" @default.
• W4386725051 modified "2023-10-03" @default.
• W4386725051 title "Active learning for medical image segmentation with stochastic batches" @default.
• W4386725051 cites W1995875735 @default.
• W4386725051 cites W2106033751 @default.
• W4386725051 cites W2462710403 @default.
• W4386725051 cites W2471138382 @default.
• W4386725051 cites W2798820905 @default.
• W4386725051 cites W2903782687 @default.
• W4386725051 cites W2911066482 @default.
• W4386725051 cites W2926307165 @default.
• W4386725051 cites W2956371155 @default.
• W4386725051 cites W2977942577 @default.
• W4386725051 cites W2986514296 @default.
• W4386725051 cites W3007986608 @default.
• W4386725051 cites W3108580372 @default.
• W4386725051 cites W3110608319 @default.
• W4386725051 cites W3117626355 @default.
• W4386725051 cites W3172681723 @default.
• W4386725051 cites W3179550234 @default.
• W4386725051 cites W3184966323 @default.
• W4386725051 cites W3214423317 @default.
• W4386725051 cites W4312507102 @default.
• W4386725051 cites W4313166273 @default.
• W4386725051 cites W4378965538 @default.
• W4386725051 cites W603830301 @default.
• W4386725051 doi "https://doi.org/10.1016/j.media.2023.102958" @default.
• W4386725051 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37769549" @default.
• W4386725051 hasPublicationYear "2023" @default.
• W4386725051 type Work @default.
• W4386725051 citedByCount "0" @default.
• W4386725051 crossrefType "journal-article" @default.
• W4386725051 hasAuthorship W4386725051A5017608284 @default.
• W4386725051 hasAuthorship W4386725051A5048401036 @default.
• W4386725051 hasAuthorship W4386725051A5064644687 @default.
• W4386725051 hasConcept C106131492 @default.
• W4386725051 hasConcept C111368507 @default.
• W4386725051 hasConcept C119857082 @default.
• W4386725051 hasConcept C124101348 @default.
• W4386725051 hasConcept C124504099 @default.
• W4386725051 hasConcept C12725497 @default.
• W4386725051 hasConcept C127313418 @default.
• W4386725051 hasConcept C140779682 @default.
• W4386725051 hasConcept C153180895 @default.
• W4386725051 hasConcept C154945302 @default.
• W4386725051 hasConcept C162324750 @default.
• W4386725051 hasConcept C176217482 @default.
• W4386725051 hasConcept C177264268 @default.
• W4386725051 hasConcept C199360897 @default.
• W4386725051 hasConcept C21547014 @default.
• W4386725051 hasConcept C2776760102 @default.
• W4386725051 hasConcept C31972630 @default.
• W4386725051 hasConcept C41008148 @default.
• W4386725051 hasConcept C77967617 @default.
• W4386725051 hasConcept C89600930 @default.
• W4386725051 hasConceptScore W4386725051C106131492 @default.
• W4386725051 hasConceptScore W4386725051C111368507 @default.
• W4386725051 hasConceptScore W4386725051C119857082 @default.
• W4386725051 hasConceptScore W4386725051C124101348 @default.
• W4386725051 hasConceptScore W4386725051C124504099 @default.
• W4386725051 hasConceptScore W4386725051C12725497 @default.
• W4386725051 hasConceptScore W4386725051C127313418 @default.
• W4386725051 hasConceptScore W4386725051C140779682 @default.
• W4386725051 hasConceptScore W4386725051C153180895 @default.
• W4386725051 hasConceptScore W4386725051C154945302 @default.
• W4386725051 hasConceptScore W4386725051C162324750 @default.
• W4386725051 hasConceptScore W4386725051C176217482 @default.
• W4386725051 hasConceptScore W4386725051C177264268 @default.
• W4386725051 hasConceptScore W4386725051C199360897 @default.
• W4386725051 hasConceptScore W4386725051C21547014 @default.
• W4386725051 hasConceptScore W4386725051C2776760102 @default.
• W4386725051 hasConceptScore W4386725051C31972630 @default.
• W4386725051 hasConceptScore W4386725051C41008148 @default.
• W4386725051 hasConceptScore W4386725051C77967617 @default.
• W4386725051 hasConceptScore W4386725051C89600930 @default.
• W4386725051 hasFunder F4320312160 @default.
• W4386725051 hasFunder F4320320994 @default.
• W4386725051 hasFunder F4320334593 @default.
• W4386725051 hasFunder F4320334841 @default.
• W4386725051 hasLocation W43867250511 @default.
• W4386725051 hasLocation W43867250512 @default.
• W4386725051 hasOpenAccess W4386725051 @default.
• W4386725051 hasPrimaryLocation W43867250511 @default.
• W4386725051 hasRelatedWork W134976887 @default.
• W4386725051 hasRelatedWork W1582206143 @default.
• W4386725051 hasRelatedWork W1840273037 @default.
• W4386725051 hasRelatedWork W2138214894 @default.
• W4386725051 hasRelatedWork W2549765251 @default.
• W4386725051 hasRelatedWork W2597787948 @default.
• W4386725051 hasRelatedWork W2734888972 @default.
• W4386725051 hasRelatedWork W3025582806 @default.
• W4386725051 hasRelatedWork W3027394838 @default.
• W4386725051 hasRelatedWork W3161321444 @default.

• next