Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200595935> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4200595935 abstract "In computer vision field, image classification as a basic image processing task has been widely concerned. This paper puts forward an efficient attention network with dilated convolution named Dilated-CBAM for image classification. The dilated convolution is applied in the backbone of the residual network to extract the residual edge path features and integrate the global information of the processed image. The amount of network parameters is greatly reduced while the receptive field is expanded, and the network parameters are learnable. By embedding our spatial attention mechanism and channel attention mechanism, the model uses FCN to strengthen the effective information in the image, weaken the invalid information, and summarize the local features of the processed image. Combining the global information and local information, the time and space for network training are saved, while the effective image features can be extracted better. In the design of attention module, this work innovatively applies residual path in attention module for combining context information inside attention mechanism without adding parameters, and helps attention module extract features of interest in image classification task more accurately. In image classification, experiment, we verify the classification effect of the Dilated-CBAM model on Cifar-10 dataset, which is 2.5% higher than ResNet-18, and reaches the classification accuracy of 93.5%. In terms of the efficiency of network training, the Dilated-CBAM reduces the number of training epochs to about 10 on the basis of CBAM model, shortens the training time to about half of the original, which greatly testifies the training efficiency." @default.
- W4200595935 created "2021-12-31" @default.
- W4200595935 creator A5021628863 @default.
- W4200595935 creator A5079667048 @default.
- W4200595935 date "2021-10-15" @default.
- W4200595935 modified "2023-10-18" @default.
- W4200595935 title "Dilated-CBAM: An Efficient Attention Network with Dilated Convolution" @default.
- W4200595935 doi "https://doi.org/10.1109/icus52573.2021.9641248" @default.
- W4200595935 hasPublicationYear "2021" @default.
- W4200595935 type Work @default.
- W4200595935 citedByCount "5" @default.
- W4200595935 countsByYear W42005959352022 @default.
- W4200595935 countsByYear W42005959352023 @default.
- W4200595935 crossrefType "proceedings-article" @default.
- W4200595935 hasAuthorship W4200595935A5021628863 @default.
- W4200595935 hasAuthorship W4200595935A5079667048 @default.
- W4200595935 hasConcept C11413529 @default.
- W4200595935 hasConcept C115961682 @default.
- W4200595935 hasConcept C127413603 @default.
- W4200595935 hasConcept C151730666 @default.
- W4200595935 hasConcept C153180895 @default.
- W4200595935 hasConcept C154945302 @default.
- W4200595935 hasConcept C155512373 @default.
- W4200595935 hasConcept C199360897 @default.
- W4200595935 hasConcept C201995342 @default.
- W4200595935 hasConcept C2777735758 @default.
- W4200595935 hasConcept C2779343474 @default.
- W4200595935 hasConcept C2780451532 @default.
- W4200595935 hasConcept C31972630 @default.
- W4200595935 hasConcept C41008148 @default.
- W4200595935 hasConcept C45347329 @default.
- W4200595935 hasConcept C50644808 @default.
- W4200595935 hasConcept C86803240 @default.
- W4200595935 hasConceptScore W4200595935C11413529 @default.
- W4200595935 hasConceptScore W4200595935C115961682 @default.
- W4200595935 hasConceptScore W4200595935C127413603 @default.
- W4200595935 hasConceptScore W4200595935C151730666 @default.
- W4200595935 hasConceptScore W4200595935C153180895 @default.
- W4200595935 hasConceptScore W4200595935C154945302 @default.
- W4200595935 hasConceptScore W4200595935C155512373 @default.
- W4200595935 hasConceptScore W4200595935C199360897 @default.
- W4200595935 hasConceptScore W4200595935C201995342 @default.
- W4200595935 hasConceptScore W4200595935C2777735758 @default.
- W4200595935 hasConceptScore W4200595935C2779343474 @default.
- W4200595935 hasConceptScore W4200595935C2780451532 @default.
- W4200595935 hasConceptScore W4200595935C31972630 @default.
- W4200595935 hasConceptScore W4200595935C41008148 @default.
- W4200595935 hasConceptScore W4200595935C45347329 @default.
- W4200595935 hasConceptScore W4200595935C50644808 @default.
- W4200595935 hasConceptScore W4200595935C86803240 @default.
- W4200595935 hasLocation W42005959351 @default.
- W4200595935 hasOpenAccess W4200595935 @default.
- W4200595935 hasPrimaryLocation W42005959351 @default.
- W4200595935 hasRelatedWork W13286208 @default.
- W4200595935 hasRelatedWork W14629346 @default.
- W4200595935 hasRelatedWork W14941219 @default.
- W4200595935 hasRelatedWork W15011695 @default.
- W4200595935 hasRelatedWork W4086350 @default.
- W4200595935 hasRelatedWork W4134551 @default.
- W4200595935 hasRelatedWork W4136762 @default.
- W4200595935 hasRelatedWork W4551069 @default.
- W4200595935 hasRelatedWork W5571305 @default.
- W4200595935 hasRelatedWork W922283 @default.
- W4200595935 isParatext "false" @default.
- W4200595935 isRetracted "false" @default.
- W4200595935 workType "article" @default.