FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285095071> ?p ?o ?g. }

• W4285095071 endingPage "3345" @default.
• W4285095071 startingPage "3345" @default.
• W4285095071 abstract "Ship detection with rotated bounding boxes in synthetic aperture radar (SAR) images is now a hot spot. However, there are still some obstacles, such as multi-scale ships, misalignment between rotated anchors and features, and the opposite requirements for spatial sensitivity of regression tasks and classification tasks. In order to solve these problems, we propose a rotated balanced feature-aligned network (RBFA-Net) where three targeted networks are designed. They are, respectively, a balanced attention feature pyramid network (BAFPN), an anchor-guided feature alignment network (AFAN) and a rotational detection network (RDN). BAFPN is an improved FPN, with attention module for fusing and enhancing multi-level features, by which we can decrease the negative impact of multi-scale ship feature differences. In AFAN, we adopt an alignment convolution layer to adaptively align the convolution features according to rotated anchor boxes for solving the misalignment problem. In RDN, we propose a task decoupling module (TDM) to adjust the feature maps, respectively, for solving the conflict between the regression task and classification task. In addition, we adopt a balanced L1 loss to balance the classification loss and regression loss. Based on the SAR rotation ship detection dataset, we conduct extensive ablation experiments and compare our RBFA-Net with eight other state-of-the-art rotated detection networks. The experiment results show that among the eight state-of-the-art rotated detection networks, RBFA-Net makes a 7.19% improvement with mean average precision compared to the second-best network." @default.
• W4285095071 created "2022-07-14" @default.
• W4285095071 creator A5031785449 @default.
• W4285095071 creator A5042956973 @default.
• W4285095071 creator A5046854149 @default.
• W4285095071 creator A5060158251 @default.
• W4285095071 creator A5082458788 @default.
• W4285095071 date "2022-07-11" @default.
• W4285095071 modified "2023-10-18" @default.
• W4285095071 title "RBFA-Net: A Rotated Balanced Feature-Aligned Network for Rotated SAR Ship Detection and Classification" @default.
• W4285095071 cites W1530000988 @default.
• W4285095071 cites W2079299474 @default.
• W4285095071 cites W2109255472 @default.
• W4285095071 cites W2253429366 @default.
• W4285095071 cites W2564429410 @default.
• W4285095071 cites W2799646862 @default.
• W4285095071 cites W2919011445 @default.
• W4285095071 cites W2928007866 @default.
• W4285095071 cites W2946589087 @default.
• W4285095071 cites W2975079793 @default.
• W4285095071 cites W2981864880 @default.
• W4285095071 cites W2986357608 @default.
• W4285095071 cites W2991363140 @default.
• W4285095071 cites W3006255335 @default.
• W4285095071 cites W3015659917 @default.
• W4285095071 cites W3017373943 @default.
• W4285095071 cites W3031154432 @default.
• W4285095071 cites W3035559754 @default.
• W4285095071 cites W3037440390 @default.
• W4285095071 cites W3044680161 @default.
• W4285095071 cites W3044749031 @default.
• W4285095071 cites W3101476123 @default.
• W4285095071 cites W3118944910 @default.
• W4285095071 cites W3119027652 @default.
• W4285095071 cites W3148432746 @default.
• W4285095071 cites W3169512507 @default.
• W4285095071 cites W3170133874 @default.
• W4285095071 cites W3178327258 @default.
• W4285095071 cites W3180954604 @default.
• W4285095071 cites W3200733355 @default.
• W4285095071 cites W3205156060 @default.
• W4285095071 cites W3206873062 @default.
• W4285095071 cites W3210550848 @default.
• W4285095071 cites W4200381407 @default.
• W4285095071 cites W4210364703 @default.
• W4285095071 cites W4212781487 @default.
• W4285095071 cites W4225833008 @default.
• W4285095071 doi "https://doi.org/10.3390/rs14143345" @default.
• W4285095071 hasPublicationYear "2022" @default.
• W4285095071 type Work @default.
• W4285095071 citedByCount "14" @default.
• W4285095071 countsByYear W42850950712022 @default.
• W4285095071 countsByYear W42850950712023 @default.
• W4285095071 crossrefType "journal-article" @default.
• W4285095071 hasAuthorship W4285095071A5031785449 @default.
• W4285095071 hasAuthorship W4285095071A5042956973 @default.
• W4285095071 hasAuthorship W4285095071A5046854149 @default.
• W4285095071 hasAuthorship W4285095071A5060158251 @default.
• W4285095071 hasAuthorship W4285095071A5082458788 @default.
• W4285095071 hasBestOaLocation W42850950711 @default.
• W4285095071 hasConcept C138885662 @default.
• W4285095071 hasConcept C142575187 @default.
• W4285095071 hasConcept C153180895 @default.
• W4285095071 hasConcept C154945302 @default.
• W4285095071 hasConcept C2524010 @default.
• W4285095071 hasConcept C2776401178 @default.
• W4285095071 hasConcept C31972630 @default.
• W4285095071 hasConcept C33923547 @default.
• W4285095071 hasConcept C41008148 @default.
• W4285095071 hasConcept C41895202 @default.
• W4285095071 hasConcept C52622490 @default.
• W4285095071 hasConcept C87360688 @default.
• W4285095071 hasConceptScore W4285095071C138885662 @default.
• W4285095071 hasConceptScore W4285095071C142575187 @default.
• W4285095071 hasConceptScore W4285095071C153180895 @default.
• W4285095071 hasConceptScore W4285095071C154945302 @default.
• W4285095071 hasConceptScore W4285095071C2524010 @default.
• W4285095071 hasConceptScore W4285095071C2776401178 @default.
• W4285095071 hasConceptScore W4285095071C31972630 @default.
• W4285095071 hasConceptScore W4285095071C33923547 @default.
• W4285095071 hasConceptScore W4285095071C41008148 @default.
• W4285095071 hasConceptScore W4285095071C41895202 @default.
• W4285095071 hasConceptScore W4285095071C52622490 @default.
• W4285095071 hasConceptScore W4285095071C87360688 @default.
• W4285095071 hasFunder F4320321001 @default.
• W4285095071 hasIssue "14" @default.
• W4285095071 hasLocation W42850950711 @default.
• W4285095071 hasOpenAccess W4285095071 @default.
• W4285095071 hasPrimaryLocation W42850950711 @default.
• W4285095071 hasRelatedWork W1504288058 @default.
• W4285095071 hasRelatedWork W1964120219 @default.
• W4285095071 hasRelatedWork W2115092356 @default.
• W4285095071 hasRelatedWork W2146076056 @default.
• W4285095071 hasRelatedWork W2167293474 @default.
• W4285095071 hasRelatedWork W2331674254 @default.
• W4285095071 hasRelatedWork W2546942002 @default.
• W4285095071 hasRelatedWork W2577364290 @default.
• W4285095071 hasRelatedWork W2811390910 @default.

• next