Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204241019> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3204241019 endingPage "511" @default.
- W3204241019 startingPage "501" @default.
- W3204241019 abstract "Computer vision based models, such as object segmentation, detection and tracking, have the potential to assist surgeons intra-operatively and improve the quality and outcomes of minimally invasive surgery. Different work streams towards instrument detection include segmentation, bounding box localisation and classification. While segmentation models offer much more granular results, bounding box annotations are easier to annotate at scale. To leverage the granularity of segmentation approaches with the scalability of bounding box-based models, a multi-task model for joint bounding box detection and segmentation of surgical instruments is proposed. The model consists of a shared backbone and three independent heads for the tasks of classification, bounding box regression, and segmentation. Using adaptive losses together with simple yet effective weakly-supervised label inference, the proposed model use weak labels to learn to segment surgical instruments with a fraction of the dataset requiring segmentation masks. Results suggest that instrument detection and segmentation tasks share intrinsic challenges and jointly learning from both reduces the burden of annotating masks at scale. Experimental validation shows that the proposed model obtain comparable results to that of single-task state-of-the-art detector and segmentation models, while only requiring a fraction of the dataset to be annotated with masks. Specifically, the proposed model obtained 0.81 weighted average precision (wAP) and 0.73 mean intersection-over-union (IOU) in the Endovis2018 dataset with 1% annotated masks, while performing joint detection and segmentation at more than 20 frames per second." @default.
- W3204241019 created "2021-10-11" @default.
- W3204241019 creator A5004212009 @default.
- W3204241019 creator A5032823221 @default.
- W3204241019 creator A5069643347 @default.
- W3204241019 creator A5077630267 @default.
- W3204241019 date "2021-01-01" @default.
- W3204241019 modified "2023-09-29" @default.
- W3204241019 title "Scalable Joint Detection and Segmentation of Surgical Instruments with Weak Supervision" @default.
- W3204241019 cites W1948593602 @default.
- W3204241019 cites W2792767783 @default.
- W3204241019 cites W2807810534 @default.
- W3204241019 cites W2894299524 @default.
- W3204241019 cites W2902067315 @default.
- W3204241019 cites W2954087924 @default.
- W3204241019 cites W2963227409 @default.
- W3204241019 cites W2963351448 @default.
- W3204241019 cites W2964187272 @default.
- W3204241019 cites W2980225217 @default.
- W3204241019 cites W3034971973 @default.
- W3204241019 cites W3096104140 @default.
- W3204241019 cites W3124802609 @default.
- W3204241019 doi "https://doi.org/10.1007/978-3-030-87196-3_47" @default.
- W3204241019 hasPublicationYear "2021" @default.
- W3204241019 type Work @default.
- W3204241019 sameAs 3204241019 @default.
- W3204241019 citedByCount "1" @default.
- W3204241019 countsByYear W32042410192023 @default.
- W3204241019 crossrefType "book-chapter" @default.
- W3204241019 hasAuthorship W3204241019A5004212009 @default.
- W3204241019 hasAuthorship W3204241019A5032823221 @default.
- W3204241019 hasAuthorship W3204241019A5069643347 @default.
- W3204241019 hasAuthorship W3204241019A5077630267 @default.
- W3204241019 hasBestOaLocation W32042410192 @default.
- W3204241019 hasConcept C115961682 @default.
- W3204241019 hasConcept C119857082 @default.
- W3204241019 hasConcept C124504099 @default.
- W3204241019 hasConcept C147037132 @default.
- W3204241019 hasConcept C153083717 @default.
- W3204241019 hasConcept C153180895 @default.
- W3204241019 hasConcept C154945302 @default.
- W3204241019 hasConcept C2776151529 @default.
- W3204241019 hasConcept C2776214188 @default.
- W3204241019 hasConcept C31972630 @default.
- W3204241019 hasConcept C41008148 @default.
- W3204241019 hasConcept C48044578 @default.
- W3204241019 hasConcept C63584917 @default.
- W3204241019 hasConcept C65885262 @default.
- W3204241019 hasConcept C77088390 @default.
- W3204241019 hasConcept C89600930 @default.
- W3204241019 hasConceptScore W3204241019C115961682 @default.
- W3204241019 hasConceptScore W3204241019C119857082 @default.
- W3204241019 hasConceptScore W3204241019C124504099 @default.
- W3204241019 hasConceptScore W3204241019C147037132 @default.
- W3204241019 hasConceptScore W3204241019C153083717 @default.
- W3204241019 hasConceptScore W3204241019C153180895 @default.
- W3204241019 hasConceptScore W3204241019C154945302 @default.
- W3204241019 hasConceptScore W3204241019C2776151529 @default.
- W3204241019 hasConceptScore W3204241019C2776214188 @default.
- W3204241019 hasConceptScore W3204241019C31972630 @default.
- W3204241019 hasConceptScore W3204241019C41008148 @default.
- W3204241019 hasConceptScore W3204241019C48044578 @default.
- W3204241019 hasConceptScore W3204241019C63584917 @default.
- W3204241019 hasConceptScore W3204241019C65885262 @default.
- W3204241019 hasConceptScore W3204241019C77088390 @default.
- W3204241019 hasConceptScore W3204241019C89600930 @default.
- W3204241019 hasLocation W32042410191 @default.
- W3204241019 hasLocation W32042410192 @default.
- W3204241019 hasLocation W32042410193 @default.
- W3204241019 hasOpenAccess W3204241019 @default.
- W3204241019 hasPrimaryLocation W32042410191 @default.
- W3204241019 hasRelatedWork W1485614034 @default.
- W3204241019 hasRelatedWork W1986943276 @default.
- W3204241019 hasRelatedWork W2112454231 @default.
- W3204241019 hasRelatedWork W2127194945 @default.
- W3204241019 hasRelatedWork W2536634271 @default.
- W3204241019 hasRelatedWork W2739874619 @default.
- W3204241019 hasRelatedWork W3111027402 @default.
- W3204241019 hasRelatedWork W4213129894 @default.
- W3204241019 hasRelatedWork W4313854567 @default.
- W3204241019 hasRelatedWork W2187221949 @default.
- W3204241019 isParatext "false" @default.
- W3204241019 isRetracted "false" @default.
- W3204241019 magId "3204241019" @default.
- W3204241019 workType "book-chapter" @default.