Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200280587> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4200280587 endingPage "102310" @default.
- W4200280587 startingPage "102310" @default.
- W4200280587 abstract "Surgical instrument segmentation plays a promising role in robot-assisted surgery. However, illumination issues often appear in surgical scenes, altering the color and texture of surgical instruments. Changes in visual features make surgical instrument segmentation difficult. To address illumination issues, the SurgiNet is proposed to learn pyramid attention features. The double attention module is designed to capture the semantic dependencies between locations and channels. Based on semantic dependencies, the semantic features in the disturbed area can be inferred for addressing illumination issues. Pyramid attention is aggregated to capture multi-scale features and make predictions more accurate. To perform model compression, class-wise self-distillation is proposed to enhance the representation learning of the network, which performs feature distillation within the class to eliminate interference from other classes. Top-down and multi-stage knowledge distillation is designed to distill class probability maps. By inter-layer supervision, high-level probability maps are applied to calibrate the probability distribution of low-level probability maps. Since class-wise distillation enhances the self-learning of the network, the network can get excellent performance with a lightweight backbone. The proposed network achieves the state-of-the-art performance of 89.14% mIoU on CataIS with only 1.66 GFlops and 2.05 M parameters. It also takes first place on EndoVis 2017 with 66.30% mIoU." @default.
- W4200280587 created "2021-12-31" @default.
- W4200280587 creator A5005968946 @default.
- W4200280587 creator A5033076846 @default.
- W4200280587 creator A5038613343 @default.
- W4200280587 creator A5039816737 @default.
- W4200280587 creator A5065297791 @default.
- W4200280587 creator A5065679716 @default.
- W4200280587 creator A5069765960 @default.
- W4200280587 date "2022-02-01" @default.
- W4200280587 modified "2023-10-15" @default.
- W4200280587 title "SurgiNet: Pyramid Attention Aggregation and Class-wise Self-Distillation for Surgical Instrument Segmentation" @default.
- W4200280587 cites W3098609708 @default.
- W4200280587 cites W4285555833 @default.
- W4200280587 doi "https://doi.org/10.1016/j.media.2021.102310" @default.
- W4200280587 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34954623" @default.
- W4200280587 hasPublicationYear "2022" @default.
- W4200280587 type Work @default.
- W4200280587 citedByCount "13" @default.
- W4200280587 countsByYear W42002805872022 @default.
- W4200280587 countsByYear W42002805872023 @default.
- W4200280587 crossrefType "journal-article" @default.
- W4200280587 hasAuthorship W4200280587A5005968946 @default.
- W4200280587 hasAuthorship W4200280587A5033076846 @default.
- W4200280587 hasAuthorship W4200280587A5038613343 @default.
- W4200280587 hasAuthorship W4200280587A5039816737 @default.
- W4200280587 hasAuthorship W4200280587A5065297791 @default.
- W4200280587 hasAuthorship W4200280587A5065679716 @default.
- W4200280587 hasAuthorship W4200280587A5069765960 @default.
- W4200280587 hasConcept C105795698 @default.
- W4200280587 hasConcept C119857082 @default.
- W4200280587 hasConcept C138885662 @default.
- W4200280587 hasConcept C142575187 @default.
- W4200280587 hasConcept C153180895 @default.
- W4200280587 hasConcept C154945302 @default.
- W4200280587 hasConcept C165064840 @default.
- W4200280587 hasConcept C17744445 @default.
- W4200280587 hasConcept C178790620 @default.
- W4200280587 hasConcept C185592680 @default.
- W4200280587 hasConcept C199539241 @default.
- W4200280587 hasConcept C204030448 @default.
- W4200280587 hasConcept C2524010 @default.
- W4200280587 hasConcept C2776359362 @default.
- W4200280587 hasConcept C2776401178 @default.
- W4200280587 hasConcept C2777212361 @default.
- W4200280587 hasConcept C31972630 @default.
- W4200280587 hasConcept C33923547 @default.
- W4200280587 hasConcept C41008148 @default.
- W4200280587 hasConcept C41895202 @default.
- W4200280587 hasConcept C89600930 @default.
- W4200280587 hasConcept C90509273 @default.
- W4200280587 hasConcept C94625758 @default.
- W4200280587 hasConceptScore W4200280587C105795698 @default.
- W4200280587 hasConceptScore W4200280587C119857082 @default.
- W4200280587 hasConceptScore W4200280587C138885662 @default.
- W4200280587 hasConceptScore W4200280587C142575187 @default.
- W4200280587 hasConceptScore W4200280587C153180895 @default.
- W4200280587 hasConceptScore W4200280587C154945302 @default.
- W4200280587 hasConceptScore W4200280587C165064840 @default.
- W4200280587 hasConceptScore W4200280587C17744445 @default.
- W4200280587 hasConceptScore W4200280587C178790620 @default.
- W4200280587 hasConceptScore W4200280587C185592680 @default.
- W4200280587 hasConceptScore W4200280587C199539241 @default.
- W4200280587 hasConceptScore W4200280587C204030448 @default.
- W4200280587 hasConceptScore W4200280587C2524010 @default.
- W4200280587 hasConceptScore W4200280587C2776359362 @default.
- W4200280587 hasConceptScore W4200280587C2776401178 @default.
- W4200280587 hasConceptScore W4200280587C2777212361 @default.
- W4200280587 hasConceptScore W4200280587C31972630 @default.
- W4200280587 hasConceptScore W4200280587C33923547 @default.
- W4200280587 hasConceptScore W4200280587C41008148 @default.
- W4200280587 hasConceptScore W4200280587C41895202 @default.
- W4200280587 hasConceptScore W4200280587C89600930 @default.
- W4200280587 hasConceptScore W4200280587C90509273 @default.
- W4200280587 hasConceptScore W4200280587C94625758 @default.
- W4200280587 hasFunder F4320321001 @default.
- W4200280587 hasFunder F4320322847 @default.
- W4200280587 hasFunder F4320335777 @default.
- W4200280587 hasFunder F4320335843 @default.
- W4200280587 hasLocation W42002805871 @default.
- W4200280587 hasLocation W42002805872 @default.
- W4200280587 hasOpenAccess W4200280587 @default.
- W4200280587 hasPrimaryLocation W42002805871 @default.
- W4200280587 hasRelatedWork W1496225612 @default.
- W4200280587 hasRelatedWork W1566843515 @default.
- W4200280587 hasRelatedWork W1972035260 @default.
- W4200280587 hasRelatedWork W2181660907 @default.
- W4200280587 hasRelatedWork W2765338038 @default.
- W4200280587 hasRelatedWork W3026162553 @default.
- W4200280587 hasRelatedWork W4249847449 @default.
- W4200280587 hasRelatedWork W4292850564 @default.
- W4200280587 hasRelatedWork W4386191828 @default.
- W4200280587 hasRelatedWork W44395729 @default.
- W4200280587 hasVolume "76" @default.
- W4200280587 isParatext "false" @default.
- W4200280587 isRetracted "false" @default.
- W4200280587 workType "article" @default.