Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000173382> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3000173382 endingPage "103876" @default.
- W3000173382 startingPage "103876" @default.
- W3000173382 abstract "Abstract The Convolutional Neural Networks (CNNs) with encoder-decoder architecture has shown powerful ability in semantic segmentation and it has also been applied in saliency detection. In most researches, the parameters of the backbone network which have been pre-trained on the ImageNet dataset will be retrained using the new training dataset to let CNNs adapt to the new task better. But the retraining will weaken generalization of the pre-trained backbone network and result in over-fitting, especially when the scale of the new training data is not very large. To make a balance between generalization and precision, and to further improve the performance of the CNNs with encoder-decoder architecture in salient object detection, we proposed a framework with enhanced backbone network (BENet). A encoder with structure of dual backbone networks (DBNs) is adopted in BENet to extract more diverse feature maps. In addition, BENet includes a connection module based on improved Res2Net to efficiently fuse feature maps from the two backbone networks and a decoder based on weighted multi-scale feedback module (WMFM) to perform synchronous learning. Our approach is extensively evaluated on six public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods without any additional supervision." @default.
- W3000173382 created "2020-01-23" @default.
- W3000173382 creator A5024239427 @default.
- W3000173382 creator A5041067519 @default.
- W3000173382 creator A5064767430 @default.
- W3000173382 date "2020-03-01" @default.
- W3000173382 modified "2023-10-14" @default.
- W3000173382 title "Salient object detection based on backbone enhanced network" @default.
- W3000173382 cites W2031489346 @default.
- W3000173382 cites W2112796928 @default.
- W3000173382 cites W2128272608 @default.
- W3000173382 cites W2735553491 @default.
- W3000173382 cites W4239147634 @default.
- W3000173382 doi "https://doi.org/10.1016/j.imavis.2020.103876" @default.
- W3000173382 hasPublicationYear "2020" @default.
- W3000173382 type Work @default.
- W3000173382 sameAs 3000173382 @default.
- W3000173382 citedByCount "7" @default.
- W3000173382 countsByYear W30001733822020 @default.
- W3000173382 countsByYear W30001733822021 @default.
- W3000173382 countsByYear W30001733822022 @default.
- W3000173382 crossrefType "journal-article" @default.
- W3000173382 hasAuthorship W3000173382A5024239427 @default.
- W3000173382 hasAuthorship W3000173382A5041067519 @default.
- W3000173382 hasAuthorship W3000173382A5064767430 @default.
- W3000173382 hasConcept C124101348 @default.
- W3000173382 hasConcept C153180895 @default.
- W3000173382 hasConcept C154945302 @default.
- W3000173382 hasConcept C2780719617 @default.
- W3000173382 hasConcept C2781238097 @default.
- W3000173382 hasConcept C31258907 @default.
- W3000173382 hasConcept C41008148 @default.
- W3000173382 hasConcept C88796919 @default.
- W3000173382 hasConceptScore W3000173382C124101348 @default.
- W3000173382 hasConceptScore W3000173382C153180895 @default.
- W3000173382 hasConceptScore W3000173382C154945302 @default.
- W3000173382 hasConceptScore W3000173382C2780719617 @default.
- W3000173382 hasConceptScore W3000173382C2781238097 @default.
- W3000173382 hasConceptScore W3000173382C31258907 @default.
- W3000173382 hasConceptScore W3000173382C41008148 @default.
- W3000173382 hasConceptScore W3000173382C88796919 @default.
- W3000173382 hasLocation W30001733821 @default.
- W3000173382 hasOpenAccess W3000173382 @default.
- W3000173382 hasPrimaryLocation W30001733821 @default.
- W3000173382 hasRelatedWork W1632853819 @default.
- W3000173382 hasRelatedWork W2032851828 @default.
- W3000173382 hasRelatedWork W2126384842 @default.
- W3000173382 hasRelatedWork W2141018987 @default.
- W3000173382 hasRelatedWork W2159581743 @default.
- W3000173382 hasRelatedWork W2536452361 @default.
- W3000173382 hasRelatedWork W2726222394 @default.
- W3000173382 hasRelatedWork W2913724016 @default.
- W3000173382 hasRelatedWork W4207035477 @default.
- W3000173382 hasRelatedWork W857879069 @default.
- W3000173382 hasVolume "95" @default.
- W3000173382 isParatext "false" @default.
- W3000173382 isRetracted "false" @default.
- W3000173382 magId "3000173382" @default.
- W3000173382 workType "article" @default.