Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284692019> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4284692019 endingPage "248" @default.
- W4284692019 startingPage "238" @default.
- W4284692019 abstract "Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies have proposed weakly-supervised methods or semi-supervised methods, they could not handle different forms of supervision simultaneously. In this paper, we proposed a novel omni-supervised object detection network, which can exploit multiple different forms of annotated data to further improve the detection performance. Specifically, the proposed network contains an omni-supervised detection head, in which each form of annotation data corresponds to a unique classification branch. Furthermore, we proposed a dynamic label assignment strategy for different annotated forms of data to facilitate better learning for each branch. Moreover, we also design a confidence-aware classification loss to emphasize the samples with high confidence and further improve the model’s performance. Extensive experiments conducted on the testing dataset show our proposed method outperforms other state-of-the-art approaches consistently, demonstrating the efficacy of deep omni-supervised learning on improving rib fracture detection performance." @default.
- W4284692019 created "2022-07-08" @default.
- W4284692019 creator A5000932451 @default.
- W4284692019 creator A5022499603 @default.
- W4284692019 creator A5027088988 @default.
- W4284692019 creator A5032708386 @default.
- W4284692019 creator A5089658384 @default.
- W4284692019 date "2022-01-01" @default.
- W4284692019 modified "2023-09-30" @default.
- W4284692019 title "ORF-Net: Deep Omni-Supervised Rib Fracture Detection from Chest CT Scans" @default.
- W4284692019 cites W1996207592 @default.
- W4284692019 cites W2048679005 @default.
- W4284692019 cites W2067733510 @default.
- W4284692019 cites W2104572878 @default.
- W4284692019 cites W2108598243 @default.
- W4284692019 cites W2194775991 @default.
- W4284692019 cites W2565639579 @default.
- W4284692019 cites W2586555845 @default.
- W4284692019 cites W2962766617 @default.
- W4284692019 cites W2963351448 @default.
- W4284692019 cites W2963785012 @default.
- W4284692019 cites W3032512901 @default.
- W4284692019 cites W3033255453 @default.
- W4284692019 cites W3035396860 @default.
- W4284692019 cites W3035406940 @default.
- W4284692019 cites W3037260676 @default.
- W4284692019 cites W3092663126 @default.
- W4284692019 cites W3107730255 @default.
- W4284692019 cites W3171468293 @default.
- W4284692019 cites W3176293577 @default.
- W4284692019 cites W3185080952 @default.
- W4284692019 cites W3204275303 @default.
- W4284692019 doi "https://doi.org/10.1007/978-3-031-16437-8_23" @default.
- W4284692019 hasPublicationYear "2022" @default.
- W4284692019 type Work @default.
- W4284692019 citedByCount "1" @default.
- W4284692019 countsByYear W42846920192023 @default.
- W4284692019 crossrefType "book-chapter" @default.
- W4284692019 hasAuthorship W4284692019A5000932451 @default.
- W4284692019 hasAuthorship W4284692019A5022499603 @default.
- W4284692019 hasAuthorship W4284692019A5027088988 @default.
- W4284692019 hasAuthorship W4284692019A5032708386 @default.
- W4284692019 hasAuthorship W4284692019A5089658384 @default.
- W4284692019 hasBestOaLocation W42846920192 @default.
- W4284692019 hasConcept C108583219 @default.
- W4284692019 hasConcept C115961682 @default.
- W4284692019 hasConcept C119857082 @default.
- W4284692019 hasConcept C136389625 @default.
- W4284692019 hasConcept C147037132 @default.
- W4284692019 hasConcept C153180895 @default.
- W4284692019 hasConcept C154945302 @default.
- W4284692019 hasConcept C165696696 @default.
- W4284692019 hasConcept C2776151529 @default.
- W4284692019 hasConcept C2776321320 @default.
- W4284692019 hasConcept C2781238097 @default.
- W4284692019 hasConcept C38652104 @default.
- W4284692019 hasConcept C41008148 @default.
- W4284692019 hasConcept C50644808 @default.
- W4284692019 hasConcept C63584917 @default.
- W4284692019 hasConceptScore W4284692019C108583219 @default.
- W4284692019 hasConceptScore W4284692019C115961682 @default.
- W4284692019 hasConceptScore W4284692019C119857082 @default.
- W4284692019 hasConceptScore W4284692019C136389625 @default.
- W4284692019 hasConceptScore W4284692019C147037132 @default.
- W4284692019 hasConceptScore W4284692019C153180895 @default.
- W4284692019 hasConceptScore W4284692019C154945302 @default.
- W4284692019 hasConceptScore W4284692019C165696696 @default.
- W4284692019 hasConceptScore W4284692019C2776151529 @default.
- W4284692019 hasConceptScore W4284692019C2776321320 @default.
- W4284692019 hasConceptScore W4284692019C2781238097 @default.
- W4284692019 hasConceptScore W4284692019C38652104 @default.
- W4284692019 hasConceptScore W4284692019C41008148 @default.
- W4284692019 hasConceptScore W4284692019C50644808 @default.
- W4284692019 hasConceptScore W4284692019C63584917 @default.
- W4284692019 hasLocation W42846920191 @default.
- W4284692019 hasLocation W42846920192 @default.
- W4284692019 hasOpenAccess W4284692019 @default.
- W4284692019 hasPrimaryLocation W42846920191 @default.
- W4284692019 hasRelatedWork W2276393162 @default.
- W4284692019 hasRelatedWork W2338698797 @default.
- W4284692019 hasRelatedWork W2736037340 @default.
- W4284692019 hasRelatedWork W2756241593 @default.
- W4284692019 hasRelatedWork W2765146509 @default.
- W4284692019 hasRelatedWork W2801801420 @default.
- W4284692019 hasRelatedWork W3110226019 @default.
- W4284692019 hasRelatedWork W3214521593 @default.
- W4284692019 hasRelatedWork W4213217366 @default.
- W4284692019 hasRelatedWork W4213376880 @default.
- W4284692019 isParatext "false" @default.
- W4284692019 isRetracted "false" @default.
- W4284692019 workType "book-chapter" @default.