Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387609223> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4387609223 endingPage "13" @default.
- W4387609223 startingPage "1" @default.
- W4387609223 abstract "It is inevitable to recognize objects in adverse weather conditions where the uncertainty of contour areas is increased. Although some multi-task learning frameworks have gained from the directional supervision between boundary detection and semantic segmentation, the interaction between those two tasks is poorly investigated. Moreover, the performance of the contour detection is expected to degrade under foggy scenarios, because the auxiliary task also has no benefits from the main task. To address the potential risk in intelligent transportation systems, this paper proposes a mutual learning framework, named CE-MGN (Confidence-Enhanced Mutual Graph Network), to propagate confidence through continuous interaction between different tasks rather than only focusing on the accuracy of the main task. The CE-MGN performs an end-to-end training paradigm and jointly learns two tasks, contour detection and semantic segmentation, through pairwise confidence-enhancement mechanism. Moreover, the task interaction is converted into graph space to further relieve the information loss during the feature aggregation in Euclidean space. Such a framework is capable to improve the robustness of respective tasks because of the encouragement from its peer task. Extensive experiments show that our CE-MGN achieved mean IoU scores of 79.35% and 79.03% on CityScapes and Foggy CityScapes datasets, respectively. Besides, our models have a stable performance on different weather severity, where the performance fluctuation is less than 1%." @default.
- W4387609223 created "2023-10-14" @default.
- W4387609223 creator A5003203521 @default.
- W4387609223 creator A5033022901 @default.
- W4387609223 creator A5045679514 @default.
- W4387609223 creator A5068762122 @default.
- W4387609223 creator A5086816845 @default.
- W4387609223 date "2023-01-01" @default.
- W4387609223 modified "2023-10-14" @default.
- W4387609223 title "Confidence-Enhanced Mutual Knowledge for Uncertain Segmentation" @default.
- W4387609223 doi "https://doi.org/10.1109/tits.2023.3309600" @default.
- W4387609223 hasPublicationYear "2023" @default.
- W4387609223 type Work @default.
- W4387609223 citedByCount "0" @default.
- W4387609223 crossrefType "journal-article" @default.
- W4387609223 hasAuthorship W4387609223A5003203521 @default.
- W4387609223 hasAuthorship W4387609223A5033022901 @default.
- W4387609223 hasAuthorship W4387609223A5045679514 @default.
- W4387609223 hasAuthorship W4387609223A5068762122 @default.
- W4387609223 hasAuthorship W4387609223A5086816845 @default.
- W4387609223 hasConcept C104317684 @default.
- W4387609223 hasConcept C119857082 @default.
- W4387609223 hasConcept C127413603 @default.
- W4387609223 hasConcept C132525143 @default.
- W4387609223 hasConcept C152139883 @default.
- W4387609223 hasConcept C153180895 @default.
- W4387609223 hasConcept C154945302 @default.
- W4387609223 hasConcept C184898388 @default.
- W4387609223 hasConcept C185592680 @default.
- W4387609223 hasConcept C201995342 @default.
- W4387609223 hasConcept C2780451532 @default.
- W4387609223 hasConcept C28006648 @default.
- W4387609223 hasConcept C41008148 @default.
- W4387609223 hasConcept C55493867 @default.
- W4387609223 hasConcept C63479239 @default.
- W4387609223 hasConcept C80444323 @default.
- W4387609223 hasConcept C89600930 @default.
- W4387609223 hasConceptScore W4387609223C104317684 @default.
- W4387609223 hasConceptScore W4387609223C119857082 @default.
- W4387609223 hasConceptScore W4387609223C127413603 @default.
- W4387609223 hasConceptScore W4387609223C132525143 @default.
- W4387609223 hasConceptScore W4387609223C152139883 @default.
- W4387609223 hasConceptScore W4387609223C153180895 @default.
- W4387609223 hasConceptScore W4387609223C154945302 @default.
- W4387609223 hasConceptScore W4387609223C184898388 @default.
- W4387609223 hasConceptScore W4387609223C185592680 @default.
- W4387609223 hasConceptScore W4387609223C201995342 @default.
- W4387609223 hasConceptScore W4387609223C2780451532 @default.
- W4387609223 hasConceptScore W4387609223C28006648 @default.
- W4387609223 hasConceptScore W4387609223C41008148 @default.
- W4387609223 hasConceptScore W4387609223C55493867 @default.
- W4387609223 hasConceptScore W4387609223C63479239 @default.
- W4387609223 hasConceptScore W4387609223C80444323 @default.
- W4387609223 hasConceptScore W4387609223C89600930 @default.
- W4387609223 hasLocation W43876092231 @default.
- W4387609223 hasOpenAccess W4387609223 @default.
- W4387609223 hasPrimaryLocation W43876092231 @default.
- W4387609223 hasRelatedWork W1692008701 @default.
- W4387609223 hasRelatedWork W2487162673 @default.
- W4387609223 hasRelatedWork W2562400057 @default.
- W4387609223 hasRelatedWork W2597588799 @default.
- W4387609223 hasRelatedWork W2793211469 @default.
- W4387609223 hasRelatedWork W2807634898 @default.
- W4387609223 hasRelatedWork W2949152769 @default.
- W4387609223 hasRelatedWork W4360593462 @default.
- W4387609223 hasRelatedWork W4372354731 @default.
- W4387609223 hasRelatedWork W2194570607 @default.
- W4387609223 isParatext "false" @default.
- W4387609223 isRetracted "false" @default.
- W4387609223 workType "article" @default.