Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221071851> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4221071851 endingPage "2633" @default.
- W4221071851 startingPage "2633" @default.
- W4221071851 abstract "Aiming at the problem of Transformers lack of local spatial receptive field and discontinuous boundary loss in rotating object detection, in this paper, we propose a Transformer-based high-precision rotating object detection model (RODFormer). Firstly, RODFormer uses a structured transformer architecture to collect feature information of different resolutions to improve the collection range of feature information. Secondly, a new feed-forward network (spatial-FFN) is constructed. Spatial-FFN fuses the local spatial features of 3 × 3 depthwise separable convolutions with the global channel features of multilayer perceptron (MLP) to solve the deficiencies of FFN in local spatial modeling. Finally, based on the space-FFN architecture, a detection head is built using the CIOU-smooth L1 loss function and only returns to the horizontal frame when the rotating frame is close to the horizontal, so as to alleviate the loss discontinuity of the rotating frame. Ablation experiments of RODFormer on the DOTA dataset show that the Transformer-structured module, the spatial-FFN module and the CIOU-smooth L1 loss function module are all effective in improving the detection accuracy of RODFormer. Compared with 12 rotating object detection models on the DOTA dataset, RODFormer has the highest average detection accuracy (up to 75.60%), that is, RODFormer is more competitive in rotating object detection accuracy." @default.
- W4221071851 created "2022-04-03" @default.
- W4221071851 creator A5030798864 @default.
- W4221071851 creator A5052865340 @default.
- W4221071851 creator A5074058834 @default.
- W4221071851 creator A5079783259 @default.
- W4221071851 creator A5088780503 @default.
- W4221071851 date "2022-03-29" @default.
- W4221071851 modified "2023-10-18" @default.
- W4221071851 title "RODFormer: High-Precision Design for Rotating Object Detection with Transformers" @default.
- W4221071851 cites W2886335102 @default.
- W4221071851 cites W3002750555 @default.
- W4221071851 cites W3003295287 @default.
- W4221071851 cites W3008470387 @default.
- W4221071851 cites W3009552135 @default.
- W4221071851 cites W3012042051 @default.
- W4221071851 cites W3093319256 @default.
- W4221071851 cites W3098218837 @default.
- W4221071851 cites W3106228955 @default.
- W4221071851 cites W3131043787 @default.
- W4221071851 cites W3132077035 @default.
- W4221071851 cites W3136761610 @default.
- W4221071851 cites W3144925525 @default.
- W4221071851 cites W3180745686 @default.
- W4221071851 cites W3187369430 @default.
- W4221071851 cites W3193494519 @default.
- W4221071851 doi "https://doi.org/10.3390/s22072633" @default.
- W4221071851 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35408247" @default.
- W4221071851 hasPublicationYear "2022" @default.
- W4221071851 type Work @default.
- W4221071851 citedByCount "6" @default.
- W4221071851 countsByYear W42210718512023 @default.
- W4221071851 crossrefType "journal-article" @default.
- W4221071851 hasAuthorship W4221071851A5030798864 @default.
- W4221071851 hasAuthorship W4221071851A5052865340 @default.
- W4221071851 hasAuthorship W4221071851A5074058834 @default.
- W4221071851 hasAuthorship W4221071851A5079783259 @default.
- W4221071851 hasAuthorship W4221071851A5088780503 @default.
- W4221071851 hasBestOaLocation W42210718511 @default.
- W4221071851 hasConcept C119599485 @default.
- W4221071851 hasConcept C127413603 @default.
- W4221071851 hasConcept C153180895 @default.
- W4221071851 hasConcept C154945302 @default.
- W4221071851 hasConcept C165801399 @default.
- W4221071851 hasConcept C2776151529 @default.
- W4221071851 hasConcept C31972630 @default.
- W4221071851 hasConcept C41008148 @default.
- W4221071851 hasConcept C66322947 @default.
- W4221071851 hasConcept C83665646 @default.
- W4221071851 hasConceptScore W4221071851C119599485 @default.
- W4221071851 hasConceptScore W4221071851C127413603 @default.
- W4221071851 hasConceptScore W4221071851C153180895 @default.
- W4221071851 hasConceptScore W4221071851C154945302 @default.
- W4221071851 hasConceptScore W4221071851C165801399 @default.
- W4221071851 hasConceptScore W4221071851C2776151529 @default.
- W4221071851 hasConceptScore W4221071851C31972630 @default.
- W4221071851 hasConceptScore W4221071851C41008148 @default.
- W4221071851 hasConceptScore W4221071851C66322947 @default.
- W4221071851 hasConceptScore W4221071851C83665646 @default.
- W4221071851 hasIssue "7" @default.
- W4221071851 hasLocation W42210718511 @default.
- W4221071851 hasLocation W42210718512 @default.
- W4221071851 hasLocation W42210718513 @default.
- W4221071851 hasLocation W42210718514 @default.
- W4221071851 hasOpenAccess W4221071851 @default.
- W4221071851 hasPrimaryLocation W42210718511 @default.
- W4221071851 hasRelatedWork W1497101000 @default.
- W4221071851 hasRelatedWork W2095705906 @default.
- W4221071851 hasRelatedWork W2730449274 @default.
- W4221071851 hasRelatedWork W2754428891 @default.
- W4221071851 hasRelatedWork W2782964878 @default.
- W4221071851 hasRelatedWork W2922421953 @default.
- W4221071851 hasRelatedWork W2980691083 @default.
- W4221071851 hasRelatedWork W3002270006 @default.
- W4221071851 hasRelatedWork W3046346900 @default.
- W4221071851 hasRelatedWork W4281560450 @default.
- W4221071851 hasVolume "22" @default.
- W4221071851 isParatext "false" @default.
- W4221071851 isRetracted "false" @default.
- W4221071851 workType "article" @default.