Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208147746> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3208147746 endingPage "311" @default.
- W3208147746 startingPage "300" @default.
- W3208147746 abstract "Domain generalization aims to enhance robustness of models to different domains, which is crucial for safety-critical systems in practice. In this paper, we propose a simple plug-in module to promote the ability of generalization for semantic segmentation networks without extra loss function. Firstly, we rethink the relationship between semantics and style in the sight of feature maps, and divide the channels of them into two kinds (i.e. style-sensitive channels and semantic-sensitive channels) via the variance of Gram matrix. Secondly, with the assumption that the domain shift mainly lies in style, a random erasure method is proposed to style-sensitive-channel features with the hope of learning domain invariant features and preventing model from over-fitting to specific domain. Extensive experiments demonstrate that the generalization of our proposed method outperforms existing approaches." @default.
- W3208147746 created "2021-11-08" @default.
- W3208147746 creator A5001711851 @default.
- W3208147746 creator A5037873810 @default.
- W3208147746 creator A5082616747 @default.
- W3208147746 date "2021-01-01" @default.
- W3208147746 modified "2023-09-23" @default.
- W3208147746 title "Suppressing Style-Sensitive Features via Randomly Erasing for Domain Generalizable Semantic Segmentation" @default.
- W3208147746 cites W1901129140 @default.
- W3208147746 cites W1903029394 @default.
- W3208147746 cites W1920962657 @default.
- W3208147746 cites W2109255472 @default.
- W3208147746 cites W2340897893 @default.
- W3208147746 cites W2412782625 @default.
- W3208147746 cites W2431874326 @default.
- W3208147746 cites W2487365028 @default.
- W3208147746 cites W2560023338 @default.
- W3208147746 cites W2781228439 @default.
- W3208147746 cites W2798658180 @default.
- W3208147746 cites W2884366600 @default.
- W3208147746 cites W2894728917 @default.
- W3208147746 cites W2963881378 @default.
- W3208147746 cites W2964309882 @default.
- W3208147746 cites W2981540341 @default.
- W3208147746 cites W3010293082 @default.
- W3208147746 cites W3035564946 @default.
- W3208147746 cites W3169545167 @default.
- W3208147746 doi "https://doi.org/10.1007/978-3-030-88013-2_25" @default.
- W3208147746 hasPublicationYear "2021" @default.
- W3208147746 type Work @default.
- W3208147746 sameAs 3208147746 @default.
- W3208147746 citedByCount "0" @default.
- W3208147746 crossrefType "book-chapter" @default.
- W3208147746 hasAuthorship W3208147746A5001711851 @default.
- W3208147746 hasAuthorship W3208147746A5037873810 @default.
- W3208147746 hasAuthorship W3208147746A5082616747 @default.
- W3208147746 hasConcept C124952713 @default.
- W3208147746 hasConcept C134306372 @default.
- W3208147746 hasConcept C142362112 @default.
- W3208147746 hasConcept C154945302 @default.
- W3208147746 hasConcept C204321447 @default.
- W3208147746 hasConcept C2776445246 @default.
- W3208147746 hasConcept C33923547 @default.
- W3208147746 hasConcept C36503486 @default.
- W3208147746 hasConcept C41008148 @default.
- W3208147746 hasConcept C89600930 @default.
- W3208147746 hasConceptScore W3208147746C124952713 @default.
- W3208147746 hasConceptScore W3208147746C134306372 @default.
- W3208147746 hasConceptScore W3208147746C142362112 @default.
- W3208147746 hasConceptScore W3208147746C154945302 @default.
- W3208147746 hasConceptScore W3208147746C204321447 @default.
- W3208147746 hasConceptScore W3208147746C2776445246 @default.
- W3208147746 hasConceptScore W3208147746C33923547 @default.
- W3208147746 hasConceptScore W3208147746C36503486 @default.
- W3208147746 hasConceptScore W3208147746C41008148 @default.
- W3208147746 hasConceptScore W3208147746C89600930 @default.
- W3208147746 hasLocation W32081477461 @default.
- W3208147746 hasOpenAccess W3208147746 @default.
- W3208147746 hasPrimaryLocation W32081477461 @default.
- W3208147746 hasRelatedWork W1552159754 @default.
- W3208147746 hasRelatedWork W2131420137 @default.
- W3208147746 hasRelatedWork W2148757832 @default.
- W3208147746 hasRelatedWork W2293457016 @default.
- W3208147746 hasRelatedWork W2368651715 @default.
- W3208147746 hasRelatedWork W2394327295 @default.
- W3208147746 hasRelatedWork W2611614995 @default.
- W3208147746 hasRelatedWork W2789919619 @default.
- W3208147746 hasRelatedWork W3107474891 @default.
- W3208147746 hasRelatedWork W4321496520 @default.
- W3208147746 isParatext "false" @default.
- W3208147746 isRetracted "false" @default.
- W3208147746 magId "3208147746" @default.
- W3208147746 workType "book-chapter" @default.