FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309163003> ?p ?o ?g. }

• W4309163003 endingPage "480" @default.
• W4309163003 startingPage "467" @default.
• W4309163003 abstract "Accurately delineating individual teeth and the gingiva in the three-dimension (3D) intraoral scanned (IOS) mesh data plays a pivotal role in many digital dental applications, e.g., orthodontics. Recent research shows that deep learning based methods can achieve promising results for 3D tooth segmentation, however, most of them rely on high-quality labeled dataset which is usually of small scales as annotating IOS meshes requires intensive human efforts. In this paper, we propose a novel self-supervised learning framework, named STSNet, to boost the performance of 3D tooth segmentation leveraging on large-scale unlabeled IOS data. The framework follows two-stage training, i.e., pre-training and fine-tuning. In pre-training, three hierarchical-level, i.e., point-level, region-level, cross-level, contrastive losses are proposed for unsupervised representation learning on a set of predefined matched points from different augmented views. The pretrained segmentation backbone is further fine-tuned in a supervised manner with a small number of labeled IOS meshes. With the same amount of annotated samples, our method can achieve an mIoU of 89.88%, significantly outperforming the supervised counterparts. The performance gain becomes more remarkable when only a small amount of labeled samples are available. Furthermore, STSNet can achieve better performance with only 40% of the annotated samples as compared to the fully supervised baselines. To the best of our knowledge, we present the first attempt of unsupervised pre-training for 3D tooth segmentation, demonstrating its strong potential in reducing human efforts for annotation and verification." @default.
• W4309163003 created "2022-11-24" @default.
• W4309163003 creator A5008311156 @default.
• W4309163003 creator A5017732456 @default.
• W4309163003 creator A5024343415 @default.
• W4309163003 creator A5030200045 @default.
• W4309163003 creator A5036068653 @default.
• W4309163003 creator A5066419480 @default.
• W4309163003 creator A5068895639 @default.
• W4309163003 creator A5079342045 @default.
• W4309163003 creator A5086664284 @default.
• W4309163003 creator A5089410490 @default.
• W4309163003 date "2023-02-01" @default.
• W4309163003 modified "2023-10-11" @default.
• W4309163003 title "Hierarchical Self-Supervised Learning for 3D Tooth Segmentation in Intra-Oral Mesh Scans" @default.
• W4309163003 cites W1974782679 @default.
• W4309163003 cites W2054969885 @default.
• W4309163003 cites W2112482836 @default.
• W4309163003 cites W2121213023 @default.
• W4309163003 cites W2156061717 @default.
• W4309163003 cites W2211722331 @default.
• W4309163003 cites W2285190206 @default.
• W4309163003 cites W2508760637 @default.
• W4309163003 cites W2553307952 @default.
• W4309163003 cites W2560609797 @default.
• W4309163003 cites W2804967795 @default.
• W4309163003 cites W2889300857 @default.
• W4309163003 cites W2913939497 @default.
• W4309163003 cites W2951864735 @default.
• W4309163003 cites W2962941647 @default.
• W4309163003 cites W2963509914 @default.
• W4309163003 cites W2979750740 @default.
• W4309163003 cites W2979822198 @default.
• W4309163003 cites W3004849003 @default.
• W4309163003 cites W3021444369 @default.
• W4309163003 cites W3028510926 @default.
• W4309163003 cites W3034675048 @default.
• W4309163003 cites W3034781633 @default.
• W4309163003 cites W3035524453 @default.
• W4309163003 cites W3100652389 @default.
• W4309163003 cites W3116959466 @default.
• W4309163003 cites W3117388369 @default.
• W4309163003 cites W3123778877 @default.
• W4309163003 cites W3156636935 @default.
• W4309163003 cites W3158405343 @default.
• W4309163003 cites W3197097949 @default.
• W4309163003 cites W3202611145 @default.
• W4309163003 cites W3203607638 @default.
• W4309163003 cites W3203717475 @default.
• W4309163003 cites W3211020964 @default.
• W4309163003 cites W3217084439 @default.
• W4309163003 cites W343636949 @default.
• W4309163003 cites W4214644223 @default.
• W4309163003 cites W4214755140 @default.
• W4309163003 cites W4312270234 @default.
• W4309163003 cites W4312310512 @default.
• W4309163003 doi "https://doi.org/10.1109/tmi.2022.3222388" @default.
• W4309163003 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36378797" @default.
• W4309163003 hasPublicationYear "2023" @default.
• W4309163003 type Work @default.
• W4309163003 citedByCount "1" @default.
• W4309163003 crossrefType "journal-article" @default.
• W4309163003 hasAuthorship W4309163003A5008311156 @default.
• W4309163003 hasAuthorship W4309163003A5017732456 @default.
• W4309163003 hasAuthorship W4309163003A5024343415 @default.
• W4309163003 hasAuthorship W4309163003A5030200045 @default.
• W4309163003 hasAuthorship W4309163003A5036068653 @default.
• W4309163003 hasAuthorship W4309163003A5066419480 @default.
• W4309163003 hasAuthorship W4309163003A5068895639 @default.
• W4309163003 hasAuthorship W4309163003A5079342045 @default.
• W4309163003 hasAuthorship W4309163003A5086664284 @default.
• W4309163003 hasAuthorship W4309163003A5089410490 @default.
• W4309163003 hasConcept C119857082 @default.
• W4309163003 hasConcept C121684516 @default.
• W4309163003 hasConcept C136389625 @default.
• W4309163003 hasConcept C153180895 @default.
• W4309163003 hasConcept C154945302 @default.
• W4309163003 hasConcept C177264268 @default.
• W4309163003 hasConcept C17744445 @default.
• W4309163003 hasConcept C199360897 @default.
• W4309163003 hasConcept C199539241 @default.
• W4309163003 hasConcept C202444582 @default.
• W4309163003 hasConcept C2776359362 @default.
• W4309163003 hasConcept C31487907 @default.
• W4309163003 hasConcept C33676613 @default.
• W4309163003 hasConcept C33923547 @default.
• W4309163003 hasConcept C41008148 @default.
• W4309163003 hasConcept C50644808 @default.
• W4309163003 hasConcept C51632099 @default.
• W4309163003 hasConcept C89600930 @default.
• W4309163003 hasConcept C94625758 @default.
• W4309163003 hasConceptScore W4309163003C119857082 @default.
• W4309163003 hasConceptScore W4309163003C121684516 @default.
• W4309163003 hasConceptScore W4309163003C136389625 @default.
• W4309163003 hasConceptScore W4309163003C153180895 @default.
• W4309163003 hasConceptScore W4309163003C154945302 @default.
• W4309163003 hasConceptScore W4309163003C177264268 @default.
• W4309163003 hasConceptScore W4309163003C17744445 @default.

• next