Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366293254> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4366293254 abstract "To improve the accuracy of cross-domain object detection, the existing unsupervised domain adaptation (UDA) object detection methods mostly use Feature Pyramid Network (FPN), multiple Region Proposal Network (RPN), and multiple domain classifier, but these methods lead to complex network structures, slow model convergence, and low detection efficiency. To solve the above problems, this paper proposes an Efficient and Accurate Cross-domain Object Detection Method Using One-level Feature and Domain Adaptation (OFDA). This method realizes one-level feature object detection through feature fusion and divide-and-conquer technology; realizes overfitting feature suppression and unsupervised domain adaptation through domain-specific suppression and domain feature alignment technology; realizes background feature suppression through the Objectness branch, which replaces the time-consuming Region Proposal Network (RPN) structure and improves the efficiency of unsupervised adaptive detection. The paper verifies the feasibility and superiority of the proposed method by the comparative experiments and ablation experiments of multiple datasets. The proposed OFDA method not only improves the efficiency of object detection, but also ensures the accuracy of cross-domain detection." @default.
- W4366293254 created "2023-04-20" @default.
- W4366293254 creator A5006219225 @default.
- W4366293254 creator A5017688381 @default.
- W4366293254 creator A5017744165 @default.
- W4366293254 creator A5030693853 @default.
- W4366293254 creator A5051434566 @default.
- W4366293254 creator A5069875119 @default.
- W4366293254 creator A5079834112 @default.
- W4366293254 creator A5082424766 @default.
- W4366293254 date "2023-06-12" @default.
- W4366293254 modified "2023-09-23" @default.
- W4366293254 title "An Efficient and Accurate Cross-Domain Object Detection Method Using One-Level Feature and Domain Adaptation" @default.
- W4366293254 cites W3096609285 @default.
- W4366293254 cites W3106250896 @default.
- W4366293254 cites W3110011650 @default.
- W4366293254 cites W3147144892 @default.
- W4366293254 cites W3206713300 @default.
- W4366293254 doi "https://doi.org/10.1142/s0218001423500167" @default.
- W4366293254 hasPublicationYear "2023" @default.
- W4366293254 type Work @default.
- W4366293254 citedByCount "0" @default.
- W4366293254 crossrefType "journal-article" @default.
- W4366293254 hasAuthorship W4366293254A5006219225 @default.
- W4366293254 hasAuthorship W4366293254A5017688381 @default.
- W4366293254 hasAuthorship W4366293254A5017744165 @default.
- W4366293254 hasAuthorship W4366293254A5030693853 @default.
- W4366293254 hasAuthorship W4366293254A5051434566 @default.
- W4366293254 hasAuthorship W4366293254A5069875119 @default.
- W4366293254 hasAuthorship W4366293254A5079834112 @default.
- W4366293254 hasAuthorship W4366293254A5082424766 @default.
- W4366293254 hasConcept C134306372 @default.
- W4366293254 hasConcept C138885662 @default.
- W4366293254 hasConcept C142575187 @default.
- W4366293254 hasConcept C153180895 @default.
- W4366293254 hasConcept C154945302 @default.
- W4366293254 hasConcept C22019652 @default.
- W4366293254 hasConcept C2524010 @default.
- W4366293254 hasConcept C2776151529 @default.
- W4366293254 hasConcept C2776401178 @default.
- W4366293254 hasConcept C31972630 @default.
- W4366293254 hasConcept C33923547 @default.
- W4366293254 hasConcept C36503486 @default.
- W4366293254 hasConcept C41008148 @default.
- W4366293254 hasConcept C41895202 @default.
- W4366293254 hasConcept C50644808 @default.
- W4366293254 hasConcept C52622490 @default.
- W4366293254 hasConcept C95623464 @default.
- W4366293254 hasConceptScore W4366293254C134306372 @default.
- W4366293254 hasConceptScore W4366293254C138885662 @default.
- W4366293254 hasConceptScore W4366293254C142575187 @default.
- W4366293254 hasConceptScore W4366293254C153180895 @default.
- W4366293254 hasConceptScore W4366293254C154945302 @default.
- W4366293254 hasConceptScore W4366293254C22019652 @default.
- W4366293254 hasConceptScore W4366293254C2524010 @default.
- W4366293254 hasConceptScore W4366293254C2776151529 @default.
- W4366293254 hasConceptScore W4366293254C2776401178 @default.
- W4366293254 hasConceptScore W4366293254C31972630 @default.
- W4366293254 hasConceptScore W4366293254C33923547 @default.
- W4366293254 hasConceptScore W4366293254C36503486 @default.
- W4366293254 hasConceptScore W4366293254C41008148 @default.
- W4366293254 hasConceptScore W4366293254C41895202 @default.
- W4366293254 hasConceptScore W4366293254C50644808 @default.
- W4366293254 hasConceptScore W4366293254C52622490 @default.
- W4366293254 hasConceptScore W4366293254C95623464 @default.
- W4366293254 hasFunder F4320321001 @default.
- W4366293254 hasFunder F4320327473 @default.
- W4366293254 hasIssue "07" @default.
- W4366293254 hasLocation W43662932541 @default.
- W4366293254 hasOpenAccess W4366293254 @default.
- W4366293254 hasPrimaryLocation W43662932541 @default.
- W4366293254 hasRelatedWork W137416770 @default.
- W4366293254 hasRelatedWork W2022996092 @default.
- W4366293254 hasRelatedWork W2090093270 @default.
- W4366293254 hasRelatedWork W2546942002 @default.
- W4366293254 hasRelatedWork W2742991909 @default.
- W4366293254 hasRelatedWork W2767651786 @default.
- W4366293254 hasRelatedWork W2784352036 @default.
- W4366293254 hasRelatedWork W2807311372 @default.
- W4366293254 hasRelatedWork W4255402425 @default.
- W4366293254 hasRelatedWork W3127217315 @default.
- W4366293254 hasVolume "37" @default.
- W4366293254 isParatext "false" @default.
- W4366293254 isRetracted "false" @default.
- W4366293254 workType "article" @default.