Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290058081> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4290058081 abstract "Multi-Label Remote Sensing Image Classification (MLRSIC) has received increasing research interest. Taking the cooccurrence relationship of multiple labels as additional information helps to improve the performance of this task. Current methods focus on using it to constrain the final feature output of a Convolutional Neural Network (CNN). On the one hand, these methods do not make full use of label correlation to form feature representation. On the other hand, they increase the label noise sensitivity of the system, resulting in poor robustness. In this paper, a novel method called Semantic Interleaving Global Channel Attention (SIGNA) is proposed for MLRSIC. First, the label co-occurrence graph is obtained according to the statistical information of the data set. The label co-occurrence graph is used as the input of the Graph Neural Network (GNN) to generate optimal feature representations. Then, the semantic features and visual features are interleaved, to guide the feature expression of the image from the original feature space to the semantic feature space with embedded label relations. SIGNA triggers global attention of feature maps channels in a new semantic feature space to extract more important visual features. Multihead SIGNA based feature adaptive weighting networks are proposed to act on any layer of CNN in a plug-and-play manner. For remote sensing images, better classification performance can be achieved by inserting CNN into the shallow layer. We conduct extensive experimental comparisons on three data sets: UCM data set, AID data set, and DFC15 data set. Experimental results demonstrate that the proposed SIGNA achieves superior classification performance compared to state-of-the-art (SOTA) methods. It is worth mentioning that the codes of this paper will be open to the community for reproducibility research. Our codes are available at https://github.com/kyle-one/SIGNA." @default.
- W4290058081 created "2022-08-06" @default.
- W4290058081 creator A5033508491 @default.
- W4290058081 creator A5042551057 @default.
- W4290058081 creator A5058737960 @default.
- W4290058081 creator A5074761778 @default.
- W4290058081 creator A5081877305 @default.
- W4290058081 date "2022-08-04" @default.
- W4290058081 modified "2023-10-17" @default.
- W4290058081 title "Semantic Interleaving Global Channel Attention for Multilabel Remote Sensing Image Classification" @default.
- W4290058081 doi "https://doi.org/10.48550/arxiv.2208.02613" @default.
- W4290058081 hasPublicationYear "2022" @default.
- W4290058081 type Work @default.
- W4290058081 citedByCount "0" @default.
- W4290058081 crossrefType "posted-content" @default.
- W4290058081 hasAuthorship W4290058081A5033508491 @default.
- W4290058081 hasAuthorship W4290058081A5042551057 @default.
- W4290058081 hasAuthorship W4290058081A5058737960 @default.
- W4290058081 hasAuthorship W4290058081A5074761778 @default.
- W4290058081 hasAuthorship W4290058081A5081877305 @default.
- W4290058081 hasBestOaLocation W42900580811 @default.
- W4290058081 hasConcept C104317684 @default.
- W4290058081 hasConcept C111919701 @default.
- W4290058081 hasConcept C124101348 @default.
- W4290058081 hasConcept C132525143 @default.
- W4290058081 hasConcept C138885662 @default.
- W4290058081 hasConcept C153180895 @default.
- W4290058081 hasConcept C154945302 @default.
- W4290058081 hasConcept C185592680 @default.
- W4290058081 hasConcept C2776401178 @default.
- W4290058081 hasConcept C2781122975 @default.
- W4290058081 hasConcept C28034677 @default.
- W4290058081 hasConcept C41008148 @default.
- W4290058081 hasConcept C41895202 @default.
- W4290058081 hasConcept C55493867 @default.
- W4290058081 hasConcept C63479239 @default.
- W4290058081 hasConcept C80444323 @default.
- W4290058081 hasConcept C81363708 @default.
- W4290058081 hasConcept C83665646 @default.
- W4290058081 hasConceptScore W4290058081C104317684 @default.
- W4290058081 hasConceptScore W4290058081C111919701 @default.
- W4290058081 hasConceptScore W4290058081C124101348 @default.
- W4290058081 hasConceptScore W4290058081C132525143 @default.
- W4290058081 hasConceptScore W4290058081C138885662 @default.
- W4290058081 hasConceptScore W4290058081C153180895 @default.
- W4290058081 hasConceptScore W4290058081C154945302 @default.
- W4290058081 hasConceptScore W4290058081C185592680 @default.
- W4290058081 hasConceptScore W4290058081C2776401178 @default.
- W4290058081 hasConceptScore W4290058081C2781122975 @default.
- W4290058081 hasConceptScore W4290058081C28034677 @default.
- W4290058081 hasConceptScore W4290058081C41008148 @default.
- W4290058081 hasConceptScore W4290058081C41895202 @default.
- W4290058081 hasConceptScore W4290058081C55493867 @default.
- W4290058081 hasConceptScore W4290058081C63479239 @default.
- W4290058081 hasConceptScore W4290058081C80444323 @default.
- W4290058081 hasConceptScore W4290058081C81363708 @default.
- W4290058081 hasConceptScore W4290058081C83665646 @default.
- W4290058081 hasLocation W42900580811 @default.
- W4290058081 hasOpenAccess W4290058081 @default.
- W4290058081 hasPrimaryLocation W42900580811 @default.
- W4290058081 hasRelatedWork W2588120994 @default.
- W4290058081 hasRelatedWork W2590243967 @default.
- W4290058081 hasRelatedWork W2760085659 @default.
- W4290058081 hasRelatedWork W2769501111 @default.
- W4290058081 hasRelatedWork W2799291336 @default.
- W4290058081 hasRelatedWork W2886673456 @default.
- W4290058081 hasRelatedWork W2981408674 @default.
- W4290058081 hasRelatedWork W3154474343 @default.
- W4290058081 hasRelatedWork W4225145356 @default.
- W4290058081 hasRelatedWork W4284989669 @default.
- W4290058081 isParatext "false" @default.
- W4290058081 isRetracted "false" @default.
- W4290058081 workType "article" @default.