Matches in SemOpenAlex for { <https://semopenalex.org/work/W3164514665> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3164514665 abstract "Domain adaption is a tool to fit models trained on a source dataset to characteristically different target samples. During training, such methods typically seek to minimize the segmentation loss, in conjunction with a penalty function for domain misalignment. State-of-the-art solutions are sensitive to heuristically chosen hyper-parameters that dictate the proportion of the two cost functions. We address this issue by introducing a novel strategy for hyper-parameter estimation via min-max optimization of the deep neural network's loss function. Our solution provides an analytical expression for the model hyper-parameters, which are iteratively estimated during training. Experimental evaluation on both synthetic data and microscopy images of ameoboid cells Entamoeba histolytica attest to the effectiveness of our solution for deep domain-adapted segmentation in bioimaging." @default.
- W3164514665 created "2021-06-07" @default.
- W3164514665 creator A5003562216 @default.
- W3164514665 creator A5043185107 @default.
- W3164514665 creator A5076283372 @default.
- W3164514665 creator A5091029927 @default.
- W3164514665 date "2021-04-13" @default.
- W3164514665 modified "2023-09-23" @default.
- W3164514665 title "A Min-Max Based Hyperparameter Estimation For Domain-Adapted Segmentation Of Amoeboid Cells" @default.
- W3164514665 cites W1983383587 @default.
- W3164514665 cites W2644685669 @default.
- W3164514665 cites W2650395120 @default.
- W3164514665 cites W2900936384 @default.
- W3164514665 cites W2908300307 @default.
- W3164514665 cites W2963820266 @default.
- W3164514665 cites W2964227007 @default.
- W3164514665 cites W2964288524 @default.
- W3164514665 cites W3014178491 @default.
- W3164514665 doi "https://doi.org/10.1109/isbi48211.2021.9433864" @default.
- W3164514665 hasPublicationYear "2021" @default.
- W3164514665 type Work @default.
- W3164514665 sameAs 3164514665 @default.
- W3164514665 citedByCount "1" @default.
- W3164514665 countsByYear W31645146652023 @default.
- W3164514665 crossrefType "proceedings-article" @default.
- W3164514665 hasAuthorship W3164514665A5003562216 @default.
- W3164514665 hasAuthorship W3164514665A5043185107 @default.
- W3164514665 hasAuthorship W3164514665A5076283372 @default.
- W3164514665 hasAuthorship W3164514665A5091029927 @default.
- W3164514665 hasConcept C108583219 @default.
- W3164514665 hasConcept C119857082 @default.
- W3164514665 hasConcept C134306372 @default.
- W3164514665 hasConcept C14036430 @default.
- W3164514665 hasConcept C153180895 @default.
- W3164514665 hasConcept C154945302 @default.
- W3164514665 hasConcept C33923547 @default.
- W3164514665 hasConcept C36503486 @default.
- W3164514665 hasConcept C41008148 @default.
- W3164514665 hasConcept C50644808 @default.
- W3164514665 hasConcept C78458016 @default.
- W3164514665 hasConcept C8642999 @default.
- W3164514665 hasConcept C86803240 @default.
- W3164514665 hasConcept C89600930 @default.
- W3164514665 hasConceptScore W3164514665C108583219 @default.
- W3164514665 hasConceptScore W3164514665C119857082 @default.
- W3164514665 hasConceptScore W3164514665C134306372 @default.
- W3164514665 hasConceptScore W3164514665C14036430 @default.
- W3164514665 hasConceptScore W3164514665C153180895 @default.
- W3164514665 hasConceptScore W3164514665C154945302 @default.
- W3164514665 hasConceptScore W3164514665C33923547 @default.
- W3164514665 hasConceptScore W3164514665C36503486 @default.
- W3164514665 hasConceptScore W3164514665C41008148 @default.
- W3164514665 hasConceptScore W3164514665C50644808 @default.
- W3164514665 hasConceptScore W3164514665C78458016 @default.
- W3164514665 hasConceptScore W3164514665C8642999 @default.
- W3164514665 hasConceptScore W3164514665C86803240 @default.
- W3164514665 hasConceptScore W3164514665C89600930 @default.
- W3164514665 hasLocation W31645146651 @default.
- W3164514665 hasOpenAccess W3164514665 @default.
- W3164514665 hasPrimaryLocation W31645146651 @default.
- W3164514665 hasRelatedWork W2790662084 @default.
- W3164514665 hasRelatedWork W2948658236 @default.
- W3164514665 hasRelatedWork W3095523211 @default.
- W3164514665 hasRelatedWork W4281616679 @default.
- W3164514665 hasRelatedWork W4283697347 @default.
- W3164514665 hasRelatedWork W4293211451 @default.
- W3164514665 hasRelatedWork W4295309597 @default.
- W3164514665 hasRelatedWork W4298144215 @default.
- W3164514665 hasRelatedWork W4307195028 @default.
- W3164514665 hasRelatedWork W4312200629 @default.
- W3164514665 isParatext "false" @default.
- W3164514665 isRetracted "false" @default.
- W3164514665 magId "3164514665" @default.
- W3164514665 workType "article" @default.