Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372279354> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4372279354 abstract "Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of information between the branches usually occurs through the concatenation or sum of the feature maps of the branches. However, this type of information exchange does not directly consider the local characteristics of the image nor the level of importance or correlation between the tasks. In this paper, we propose a semantic segmentation method, MTLSegFormer, which combines multi-task learning and attention mechanisms. After the backbone feature extraction, two feature maps are learned for each task. The first map is proposed to learn features related to its task, while the second map is obtained by applying learned visual attention to locally re-weigh the feature maps of the other tasks. In this way, weights are assigned to local regions of the image of other tasks that have greater importance for the specific task. Finally, the two maps are combined and used to solve a task. We tested the performance in two challenging problems with correlated tasks and observed a significant improvement in accuracy, mainly in tasks with high dependence on the others." @default.
- W4372279354 created "2023-05-07" @default.
- W4372279354 creator A5007144110 @default.
- W4372279354 creator A5017880637 @default.
- W4372279354 creator A5034562479 @default.
- W4372279354 creator A5034745689 @default.
- W4372279354 creator A5056451074 @default.
- W4372279354 creator A5069566549 @default.
- W4372279354 creator A5074989797 @default.
- W4372279354 date "2023-05-04" @default.
- W4372279354 modified "2023-09-23" @default.
- W4372279354 title "MTLSegFormer: Multi-task Learning with Transformers for Semantic Segmentation in Precision Agriculture" @default.
- W4372279354 doi "https://doi.org/10.48550/arxiv.2305.02813" @default.
- W4372279354 hasPublicationYear "2023" @default.
- W4372279354 type Work @default.
- W4372279354 citedByCount "0" @default.
- W4372279354 crossrefType "posted-content" @default.
- W4372279354 hasAuthorship W4372279354A5007144110 @default.
- W4372279354 hasAuthorship W4372279354A5017880637 @default.
- W4372279354 hasAuthorship W4372279354A5034562479 @default.
- W4372279354 hasAuthorship W4372279354A5034745689 @default.
- W4372279354 hasAuthorship W4372279354A5056451074 @default.
- W4372279354 hasAuthorship W4372279354A5069566549 @default.
- W4372279354 hasAuthorship W4372279354A5074989797 @default.
- W4372279354 hasBestOaLocation W43722793541 @default.
- W4372279354 hasConcept C114614502 @default.
- W4372279354 hasConcept C119599485 @default.
- W4372279354 hasConcept C119857082 @default.
- W4372279354 hasConcept C127413603 @default.
- W4372279354 hasConcept C138885662 @default.
- W4372279354 hasConcept C153180895 @default.
- W4372279354 hasConcept C154945302 @default.
- W4372279354 hasConcept C165801399 @default.
- W4372279354 hasConcept C201995342 @default.
- W4372279354 hasConcept C2776401178 @default.
- W4372279354 hasConcept C2780451532 @default.
- W4372279354 hasConcept C28006648 @default.
- W4372279354 hasConcept C33923547 @default.
- W4372279354 hasConcept C41008148 @default.
- W4372279354 hasConcept C41895202 @default.
- W4372279354 hasConcept C52622490 @default.
- W4372279354 hasConcept C66322947 @default.
- W4372279354 hasConcept C87619178 @default.
- W4372279354 hasConcept C89600930 @default.
- W4372279354 hasConceptScore W4372279354C114614502 @default.
- W4372279354 hasConceptScore W4372279354C119599485 @default.
- W4372279354 hasConceptScore W4372279354C119857082 @default.
- W4372279354 hasConceptScore W4372279354C127413603 @default.
- W4372279354 hasConceptScore W4372279354C138885662 @default.
- W4372279354 hasConceptScore W4372279354C153180895 @default.
- W4372279354 hasConceptScore W4372279354C154945302 @default.
- W4372279354 hasConceptScore W4372279354C165801399 @default.
- W4372279354 hasConceptScore W4372279354C201995342 @default.
- W4372279354 hasConceptScore W4372279354C2776401178 @default.
- W4372279354 hasConceptScore W4372279354C2780451532 @default.
- W4372279354 hasConceptScore W4372279354C28006648 @default.
- W4372279354 hasConceptScore W4372279354C33923547 @default.
- W4372279354 hasConceptScore W4372279354C41008148 @default.
- W4372279354 hasConceptScore W4372279354C41895202 @default.
- W4372279354 hasConceptScore W4372279354C52622490 @default.
- W4372279354 hasConceptScore W4372279354C66322947 @default.
- W4372279354 hasConceptScore W4372279354C87619178 @default.
- W4372279354 hasConceptScore W4372279354C89600930 @default.
- W4372279354 hasLocation W43722793541 @default.
- W4372279354 hasOpenAccess W4372279354 @default.
- W4372279354 hasPrimaryLocation W43722793541 @default.
- W4372279354 hasRelatedWork W1964120219 @default.
- W4372279354 hasRelatedWork W2016461833 @default.
- W4372279354 hasRelatedWork W2136054869 @default.
- W4372279354 hasRelatedWork W2144059113 @default.
- W4372279354 hasRelatedWork W2146076056 @default.
- W4372279354 hasRelatedWork W2382607599 @default.
- W4372279354 hasRelatedWork W2811390910 @default.
- W4372279354 hasRelatedWork W3003836766 @default.
- W4372279354 hasRelatedWork W3197541072 @default.
- W4372279354 hasRelatedWork W4352981569 @default.
- W4372279354 isParatext "false" @default.
- W4372279354 isRetracted "false" @default.
- W4372279354 workType "article" @default.