Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366223417> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4366223417 endingPage "99" @default.
- W4366223417 startingPage "85" @default.
- W4366223417 abstract "Deep Convolutional Neural Networks (CNNs) have achieved impressive performance in edge detection tasks, but their large number of parameters often leads to high memory and energy costs for implementation on lightweight devices. In this paper, we propose a new architecture, called Efficient Deep-learning Gradients Extraction Network (EDGE-Net), that integrates the advantages of Depthwise Separable Convolutions and deformable convolutional networks (DeformableConvNet) to address these inefficiencies. By carefully selecting proper components and utilizing network pruning techniques, our proposed EDGE-Net achieves state-of-the-art accuracy in edge detection while significantly reducing complexity. Experimental results on BSDS500 and NYUDv2 datasets demonstrate that EDGE-Net outperforms current lightweight edge detectors with only 500k parameters, without relying on pre-trained weights." @default.
- W4366223417 created "2023-04-19" @default.
- W4366223417 creator A5000153604 @default.
- W4366223417 creator A5067460929 @default.
- W4366223417 date "2023-03-30" @default.
- W4366223417 modified "2023-09-25" @default.
- W4366223417 title "EDGE-Net: Efficient Deep-Learning Gradients Extraction Network" @default.
- W4366223417 doi "https://doi.org/10.5121/ijaia.2023.14207" @default.
- W4366223417 hasPublicationYear "2023" @default.
- W4366223417 type Work @default.
- W4366223417 citedByCount "0" @default.
- W4366223417 crossrefType "journal-article" @default.
- W4366223417 hasAuthorship W4366223417A5000153604 @default.
- W4366223417 hasAuthorship W4366223417A5067460929 @default.
- W4366223417 hasConcept C108010975 @default.
- W4366223417 hasConcept C108583219 @default.
- W4366223417 hasConcept C111919701 @default.
- W4366223417 hasConcept C138236772 @default.
- W4366223417 hasConcept C14166107 @default.
- W4366223417 hasConcept C153180895 @default.
- W4366223417 hasConcept C154945302 @default.
- W4366223417 hasConcept C162307627 @default.
- W4366223417 hasConcept C2524010 @default.
- W4366223417 hasConcept C2778456923 @default.
- W4366223417 hasConcept C33923547 @default.
- W4366223417 hasConcept C41008148 @default.
- W4366223417 hasConcept C6557445 @default.
- W4366223417 hasConcept C79974875 @default.
- W4366223417 hasConcept C81363708 @default.
- W4366223417 hasConcept C86803240 @default.
- W4366223417 hasConceptScore W4366223417C108010975 @default.
- W4366223417 hasConceptScore W4366223417C108583219 @default.
- W4366223417 hasConceptScore W4366223417C111919701 @default.
- W4366223417 hasConceptScore W4366223417C138236772 @default.
- W4366223417 hasConceptScore W4366223417C14166107 @default.
- W4366223417 hasConceptScore W4366223417C153180895 @default.
- W4366223417 hasConceptScore W4366223417C154945302 @default.
- W4366223417 hasConceptScore W4366223417C162307627 @default.
- W4366223417 hasConceptScore W4366223417C2524010 @default.
- W4366223417 hasConceptScore W4366223417C2778456923 @default.
- W4366223417 hasConceptScore W4366223417C33923547 @default.
- W4366223417 hasConceptScore W4366223417C41008148 @default.
- W4366223417 hasConceptScore W4366223417C6557445 @default.
- W4366223417 hasConceptScore W4366223417C79974875 @default.
- W4366223417 hasConceptScore W4366223417C81363708 @default.
- W4366223417 hasConceptScore W4366223417C86803240 @default.
- W4366223417 hasIssue "2" @default.
- W4366223417 hasLocation W43662234171 @default.
- W4366223417 hasOpenAccess W4366223417 @default.
- W4366223417 hasPrimaryLocation W43662234171 @default.
- W4366223417 hasRelatedWork W2732542196 @default.
- W4366223417 hasRelatedWork W2738221750 @default.
- W4366223417 hasRelatedWork W2921728822 @default.
- W4366223417 hasRelatedWork W2966011162 @default.
- W4366223417 hasRelatedWork W3015440700 @default.
- W4366223417 hasRelatedWork W3126969908 @default.
- W4366223417 hasRelatedWork W4214561993 @default.
- W4366223417 hasRelatedWork W4293869292 @default.
- W4366223417 hasRelatedWork W4313526662 @default.
- W4366223417 hasRelatedWork W564581980 @default.
- W4366223417 hasVolume "14" @default.
- W4366223417 isParatext "false" @default.
- W4366223417 isRetracted "false" @default.
- W4366223417 workType "article" @default.