Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211462> ?p ?o ?g. }
- W4387211462 endingPage "636" @default.
- W4387211462 startingPage "625" @default.
- W4387211462 abstract "Medical imaging segmentation is a critical key task for computer-assisted diagnosis and disease monitoring. However, collecting a large-scale medical dataset with well-annotation is time-consuming and requires domain knowledge. Reducing the number of annotations poses two challenges: obtaining sufficient supervision and generating high-quality pseudo labels. To address these, we propose a universal framework for annotation-efficient medical segmentation, which is capable of handling both scribble-supervised and point-supervised segmentation. Our approach includes an auxiliary reconstruction branch that provides more supervision and backwards sufficient gradients for learning visual representations. Besides, a novel pseudo label generation branch utilizes the Vector Quantization (VQ) bank to store texture-oriented and global features for generating pseudo labels. To boost the model training, we generate the high-quality pseudo labels by mixing the segmentation prediction and pseudo labels from the VQ bank. The experimental results on the ACDC MRI segmentation dataset demonstrate effectiveness of our designed method. We obtain a comparable performance (0.86 vs. 0.87 DSC score) with a few points." @default.
- W4387211462 created "2023-10-01" @default.
- W4387211462 creator A5001599295 @default.
- W4387211462 creator A5010970485 @default.
- W4387211462 creator A5017061083 @default.
- W4387211462 creator A5033080900 @default.
- W4387211462 creator A5036903821 @default.
- W4387211462 creator A5067953198 @default.
- W4387211462 creator A5087747620 @default.
- W4387211462 date "2023-01-01" @default.
- W4387211462 modified "2023-10-01" @default.
- W4387211462 title "Minimal-Supervised Medical Image Segmentation via Vector Quantization Memory" @default.
- W4387211462 cites W1901129140 @default.
- W4387211462 cites W2124351162 @default.
- W4387211462 cites W2125637308 @default.
- W4387211462 cites W2337429362 @default.
- W4387211462 cites W2750925197 @default.
- W4387211462 cites W2751665805 @default.
- W4387211462 cites W2804047627 @default.
- W4387211462 cites W2963073217 @default.
- W4387211462 cites W2963198662 @default.
- W4387211462 cites W2979907638 @default.
- W4387211462 cites W3083779147 @default.
- W4387211462 cites W3092564080 @default.
- W4387211462 cites W3094901756 @default.
- W4387211462 cites W3103562302 @default.
- W4387211462 cites W3112701542 @default.
- W4387211462 cites W3152004749 @default.
- W4387211462 cites W3171581326 @default.
- W4387211462 cites W3174890219 @default.
- W4387211462 cites W3199073632 @default.
- W4387211462 cites W3199551447 @default.
- W4387211462 cites W3202876959 @default.
- W4387211462 cites W3203046931 @default.
- W4387211462 cites W3203488660 @default.
- W4387211462 cites W3204025806 @default.
- W4387211462 cites W3204322147 @default.
- W4387211462 cites W4214637271 @default.
- W4387211462 cites W4295747223 @default.
- W4387211462 cites W4295747380 @default.
- W4387211462 doi "https://doi.org/10.1007/978-3-031-43898-1_60" @default.
- W4387211462 hasPublicationYear "2023" @default.
- W4387211462 type Work @default.
- W4387211462 citedByCount "0" @default.
- W4387211462 crossrefType "book-chapter" @default.
- W4387211462 hasAuthorship W4387211462A5001599295 @default.
- W4387211462 hasAuthorship W4387211462A5010970485 @default.
- W4387211462 hasAuthorship W4387211462A5017061083 @default.
- W4387211462 hasAuthorship W4387211462A5033080900 @default.
- W4387211462 hasAuthorship W4387211462A5036903821 @default.
- W4387211462 hasAuthorship W4387211462A5067953198 @default.
- W4387211462 hasAuthorship W4387211462A5087747620 @default.
- W4387211462 hasConcept C119857082 @default.
- W4387211462 hasConcept C124504099 @default.
- W4387211462 hasConcept C125308379 @default.
- W4387211462 hasConcept C136389625 @default.
- W4387211462 hasConcept C144133560 @default.
- W4387211462 hasConcept C153180895 @default.
- W4387211462 hasConcept C154945302 @default.
- W4387211462 hasConcept C162853370 @default.
- W4387211462 hasConcept C199833920 @default.
- W4387211462 hasConcept C2776321320 @default.
- W4387211462 hasConcept C31972630 @default.
- W4387211462 hasConcept C40567965 @default.
- W4387211462 hasConcept C41008148 @default.
- W4387211462 hasConcept C50644808 @default.
- W4387211462 hasConcept C65885262 @default.
- W4387211462 hasConcept C89600930 @default.
- W4387211462 hasConceptScore W4387211462C119857082 @default.
- W4387211462 hasConceptScore W4387211462C124504099 @default.
- W4387211462 hasConceptScore W4387211462C125308379 @default.
- W4387211462 hasConceptScore W4387211462C136389625 @default.
- W4387211462 hasConceptScore W4387211462C144133560 @default.
- W4387211462 hasConceptScore W4387211462C153180895 @default.
- W4387211462 hasConceptScore W4387211462C154945302 @default.
- W4387211462 hasConceptScore W4387211462C162853370 @default.
- W4387211462 hasConceptScore W4387211462C199833920 @default.
- W4387211462 hasConceptScore W4387211462C2776321320 @default.
- W4387211462 hasConceptScore W4387211462C31972630 @default.
- W4387211462 hasConceptScore W4387211462C40567965 @default.
- W4387211462 hasConceptScore W4387211462C41008148 @default.
- W4387211462 hasConceptScore W4387211462C50644808 @default.
- W4387211462 hasConceptScore W4387211462C65885262 @default.
- W4387211462 hasConceptScore W4387211462C89600930 @default.
- W4387211462 hasLocation W43872114621 @default.
- W4387211462 hasOpenAccess W4387211462 @default.
- W4387211462 hasPrimaryLocation W43872114621 @default.
- W4387211462 hasRelatedWork W134976887 @default.
- W4387211462 hasRelatedWork W1669643531 @default.
- W4387211462 hasRelatedWork W1982826852 @default.
- W4387211462 hasRelatedWork W2005437358 @default.
- W4387211462 hasRelatedWork W2110230079 @default.
- W4387211462 hasRelatedWork W2384989255 @default.
- W4387211462 hasRelatedWork W2517104666 @default.
- W4387211462 hasRelatedWork W2549936415 @default.
- W4387211462 hasRelatedWork W2566648451 @default.
- W4387211462 hasRelatedWork W1967061043 @default.
- W4387211462 isParatext "false" @default.