FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367171996> ?p ?o ?g. }

• W4367171996 endingPage "126273" @default.
• W4367171996 startingPage "126273" @default.
• W4367171996 abstract "Domain generalization semantic segmentation methods aim to generalize well on out-of-distribution scenes, which is crucial for real-world applications. Recent works focus on learning domain-invariant content information by using normalization, whitening, and domain randomization to remove style information. Although these methods improve the performance on out-of-distribution scenes to some extent, they ignore the learning of edge and semantic layout information. The edge information describes the shape and boundary of an object and the semantic layout information contains the common sense priors (e.g., the spatial position of objects). For one thing, we observe that the shape of the same object with different styles is domain-invariant in the edge map. For another, we observe that the common sense priors in the semantic layout information of different scenes are domain-invariant. Motivated by these observations, a novel approach is proposed for domain generalization semantic segmentation by using the edge and semantic layout information. Specifically, the proposed approach contains the edge reconstruction module (ERM), the semantic layout reconstruction module (SLRM), and the triple information aggregation module (TIAM). The ERM and SLRM aim to explicitly learn the edge and semantic layout information. The TIAM aggregates the edge and semantic layout information to refine the content information. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on domain generalization segmentation tasks. The source code will be released at https://github.com/seabearlmx/DIIA." @default.
• W4367171996 created "2023-04-28" @default.
• W4367171996 creator A5000209211 @default.
• W4367171996 creator A5002688054 @default.
• W4367171996 creator A5035616324 @default.
• W4367171996 creator A5035717024 @default.
• W4367171996 creator A5076929850 @default.
• W4367171996 creator A5079738340 @default.
• W4367171996 date "2023-08-01" @default.
• W4367171996 modified "2023-09-28" @default.
• W4367171996 title "Domain-invariant information aggregation for domain generalization semantic segmentation" @default.
• W4367171996 cites W2194775991 @default.
• W4367171996 cites W2266390837 @default.
• W4367171996 cites W2340897893 @default.
• W4367171996 cites W2412782625 @default.
• W4367171996 cites W2431874326 @default.
• W4367171996 cites W2603777577 @default.
• W4367171996 cites W2781228439 @default.
• W4367171996 cites W2790696291 @default.
• W4367171996 cites W2883780447 @default.
• W4367171996 cites W2884366600 @default.
• W4367171996 cites W2895281799 @default.
• W4367171996 cites W2917102740 @default.
• W4367171996 cites W2932414082 @default.
• W4367171996 cites W2955058313 @default.
• W4367171996 cites W2962793481 @default.
• W4367171996 cites W2962872526 @default.
• W4367171996 cites W2963163009 @default.
• W4367171996 cites W2964309882 @default.
• W4367171996 cites W2979792663 @default.
• W4367171996 cites W2981488580 @default.
• W4367171996 cites W2981540341 @default.
• W4367171996 cites W2981689412 @default.
• W4367171996 cites W2984711682 @default.
• W4367171996 cites W2991471181 @default.
• W4367171996 cites W3092557432 @default.
• W4367171996 cites W3155265425 @default.
• W4367171996 cites W3169545167 @default.
• W4367171996 cites W3170204166 @default.
• W4367171996 cites W3171920444 @default.
• W4367171996 cites W3177052299 @default.
• W4367171996 cites W3180439858 @default.
• W4367171996 cites W3181515393 @default.
• W4367171996 cites W3196835455 @default.
• W4367171996 cites W3197017665 @default.
• W4367171996 cites W3198062544 @default.
• W4367171996 cites W3202115483 @default.
• W4367171996 cites W3202422321 @default.
• W4367171996 cites W3208144678 @default.
• W4367171996 cites W3210259784 @default.
• W4367171996 cites W3217147624 @default.
• W4367171996 cites W4283803529 @default.
• W4367171996 cites W4295046678 @default.
• W4367171996 cites W4312426709 @default.
• W4367171996 cites W4312657985 @default.
• W4367171996 cites W4312719508 @default.
• W4367171996 cites W4313045831 @default.
• W4367171996 cites W4323338514 @default.
• W4367171996 doi "https://doi.org/10.1016/j.neucom.2023.126273" @default.
• W4367171996 hasPublicationYear "2023" @default.
• W4367171996 type Work @default.
• W4367171996 citedByCount "1" @default.
• W4367171996 countsByYear W43671719962023 @default.
• W4367171996 crossrefType "journal-article" @default.
• W4367171996 hasAuthorship W4367171996A5000209211 @default.
• W4367171996 hasAuthorship W4367171996A5002688054 @default.
• W4367171996 hasAuthorship W4367171996A5035616324 @default.
• W4367171996 hasAuthorship W4367171996A5035717024 @default.
• W4367171996 hasAuthorship W4367171996A5076929850 @default.
• W4367171996 hasAuthorship W4367171996A5079738340 @default.
• W4367171996 hasConcept C153180895 @default.
• W4367171996 hasConcept C154945302 @default.
• W4367171996 hasConcept C23123220 @default.
• W4367171996 hasConcept C31972630 @default.
• W4367171996 hasConcept C41008148 @default.
• W4367171996 hasConcept C89600930 @default.
• W4367171996 hasConceptScore W4367171996C153180895 @default.
• W4367171996 hasConceptScore W4367171996C154945302 @default.
• W4367171996 hasConceptScore W4367171996C23123220 @default.
• W4367171996 hasConceptScore W4367171996C31972630 @default.
• W4367171996 hasConceptScore W4367171996C41008148 @default.
• W4367171996 hasConceptScore W4367171996C89600930 @default.
• W4367171996 hasLocation W43671719961 @default.
• W4367171996 hasOpenAccess W4367171996 @default.
• W4367171996 hasPrimaryLocation W43671719961 @default.
• W4367171996 hasRelatedWork W1669643531 @default.
• W4367171996 hasRelatedWork W1982826852 @default.
• W4367171996 hasRelatedWork W2005437358 @default.
• W4367171996 hasRelatedWork W2008656436 @default.
• W4367171996 hasRelatedWork W2023558673 @default.
• W4367171996 hasRelatedWork W2110230079 @default.
• W4367171996 hasRelatedWork W2134924024 @default.
• W4367171996 hasRelatedWork W2517104666 @default.
• W4367171996 hasRelatedWork W2613186388 @default.
• W4367171996 hasRelatedWork W1967061043 @default.
• W4367171996 hasVolume "546" @default.
• W4367171996 isParatext "false" @default.
• W4367171996 isRetracted "false" @default.

• next