Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296195809> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4296195809 endingPage "127" @default.
- W4296195809 startingPage "117" @default.
- W4296195809 abstract "Self-knowledge distillation (SKD) is a recent and promising machine learning approach where a shallow student network is trained to distill its own knowledge. By contrast, in traditional knowledge distillation a student model distills its knowledge from a large teacher network model, which involves vast computational complexity and a large storage size. Consequently, SKD is a useful approach to model medical imaging problems with scarce data. We propose an original SKD framework to predict where a sonographer should look next using a multi-modal ultrasound and gaze dataset. We design a novel Wide Feature Distillation module, which is applied to intermediate feature maps in the form of transformations. The module applies a more refined feature map filtering which is important when predicting gaze for the fetal anatomy variable in size. Our architecture design includes ReSL loss that enables a student network to learn useful information whilst discarding the rest. The proposed network is validated on a large multi-modal ultrasound dataset, which is acquired during routine first trimester fetal ultrasound scanning. Experimental results show the novel SKD approach outperforms alternative state-of-the-art architectures on all saliency metrics." @default.
- W4296195809 created "2022-09-18" @default.
- W4296195809 creator A5000401182 @default.
- W4296195809 creator A5015592249 @default.
- W4296195809 creator A5042467582 @default.
- W4296195809 creator A5076657548 @default.
- W4296195809 creator A5091436544 @default.
- W4296195809 date "2022-01-01" @default.
- W4296195809 modified "2023-09-26" @default.
- W4296195809 title "Self-Knowledge Distillation for First Trimester Ultrasound Saliency Prediction" @default.
- W4296195809 cites W1901129140 @default.
- W4296195809 cites W2097117768 @default.
- W4296195809 cites W2194775991 @default.
- W4296195809 cites W2904170036 @default.
- W4296195809 cites W2952787292 @default.
- W4296195809 cites W2954054736 @default.
- W4296195809 cites W2962235052 @default.
- W4296195809 cites W2964309882 @default.
- W4296195809 cites W2982157312 @default.
- W4296195809 cites W2987861506 @default.
- W4296195809 cites W2998544007 @default.
- W4296195809 cites W3005193778 @default.
- W4296195809 cites W3034695001 @default.
- W4296195809 cites W3034971973 @default.
- W4296195809 cites W3044261867 @default.
- W4296195809 cites W3090336986 @default.
- W4296195809 cites W3095187889 @default.
- W4296195809 cites W3182723337 @default.
- W4296195809 cites W3185556852 @default.
- W4296195809 cites W3185613252 @default.
- W4296195809 cites W3203297015 @default.
- W4296195809 cites W3203395150 @default.
- W4296195809 cites W3204245437 @default.
- W4296195809 doi "https://doi.org/10.1007/978-3-031-16902-1_12" @default.
- W4296195809 hasPublicationYear "2022" @default.
- W4296195809 type Work @default.
- W4296195809 citedByCount "0" @default.
- W4296195809 crossrefType "book-chapter" @default.
- W4296195809 hasAuthorship W4296195809A5000401182 @default.
- W4296195809 hasAuthorship W4296195809A5015592249 @default.
- W4296195809 hasAuthorship W4296195809A5042467582 @default.
- W4296195809 hasAuthorship W4296195809A5076657548 @default.
- W4296195809 hasAuthorship W4296195809A5091436544 @default.
- W4296195809 hasBestOaLocation W42961958092 @default.
- W4296195809 hasConcept C119857082 @default.
- W4296195809 hasConcept C121332964 @default.
- W4296195809 hasConcept C138885662 @default.
- W4296195809 hasConcept C143753070 @default.
- W4296195809 hasConcept C153180895 @default.
- W4296195809 hasConcept C154945302 @default.
- W4296195809 hasConcept C178790620 @default.
- W4296195809 hasConcept C185592680 @default.
- W4296195809 hasConcept C204030448 @default.
- W4296195809 hasConcept C24890656 @default.
- W4296195809 hasConcept C2776401178 @default.
- W4296195809 hasConcept C2778941581 @default.
- W4296195809 hasConcept C41008148 @default.
- W4296195809 hasConcept C41895202 @default.
- W4296195809 hasConcept C50644808 @default.
- W4296195809 hasConceptScore W4296195809C119857082 @default.
- W4296195809 hasConceptScore W4296195809C121332964 @default.
- W4296195809 hasConceptScore W4296195809C138885662 @default.
- W4296195809 hasConceptScore W4296195809C143753070 @default.
- W4296195809 hasConceptScore W4296195809C153180895 @default.
- W4296195809 hasConceptScore W4296195809C154945302 @default.
- W4296195809 hasConceptScore W4296195809C178790620 @default.
- W4296195809 hasConceptScore W4296195809C185592680 @default.
- W4296195809 hasConceptScore W4296195809C204030448 @default.
- W4296195809 hasConceptScore W4296195809C24890656 @default.
- W4296195809 hasConceptScore W4296195809C2776401178 @default.
- W4296195809 hasConceptScore W4296195809C2778941581 @default.
- W4296195809 hasConceptScore W4296195809C41008148 @default.
- W4296195809 hasConceptScore W4296195809C41895202 @default.
- W4296195809 hasConceptScore W4296195809C50644808 @default.
- W4296195809 hasLocation W42961958091 @default.
- W4296195809 hasLocation W42961958092 @default.
- W4296195809 hasOpenAccess W4296195809 @default.
- W4296195809 hasPrimaryLocation W42961958091 @default.
- W4296195809 hasRelatedWork W2016461833 @default.
- W4296195809 hasRelatedWork W2052253960 @default.
- W4296195809 hasRelatedWork W2147802381 @default.
- W4296195809 hasRelatedWork W2382607599 @default.
- W4296195809 hasRelatedWork W2546942002 @default.
- W4296195809 hasRelatedWork W2760085659 @default.
- W4296195809 hasRelatedWork W2787306535 @default.
- W4296195809 hasRelatedWork W2929240682 @default.
- W4296195809 hasRelatedWork W3197541072 @default.
- W4296195809 hasRelatedWork W1629725936 @default.
- W4296195809 isParatext "false" @default.
- W4296195809 isRetracted "false" @default.
- W4296195809 workType "book-chapter" @default.