FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129297821> ?p ?o ?g. }

• W3129297821 abstract "Convolutional Neural Networks (CNNs) have been successfully applied for relative camera pose estimation from labeled image-pair data, without requiring any handengineered features, camera intrinsic parameters or depth information. The trained CNN can be utilized for performing pose based visual servo control (PBVS). One of the ways to improve the quality of visual servo output is to improve the accuracy of the CNN for estimating the relative pose estimation. With a given state-of-the-art CNN for relative pose regression, how can we achieve an improved performance for visual servo control? In this paper, we explore switching of CNNs to improve the precision of visual servo control. The idea of switching a CNN is due to the fact that the dataset for training a relative camera pose regressor for visual servo control must contain variations in relative pose ranging from a very small scale to eventually a larger scale. We found that, training two different instances of the CNN, one for large-scale-displacements (LSD) and another for small-scale-displacements (SSD) and switching them during the visual servo execution yields better results than training a single CNN with the combined LSD+SSD data. However, it causes extra storage overhead and switching decision is taken by a manually set threshold which may not be optimal for all the scenes. To eliminate these drawbacks, we propose an efficient switching strategy based on model agnostic meta learning (MAML) algorithm. In this, a single model is trained to learn parameters which are simultaneously good for multiple tasks, namely a binary classification for switching decision, a 6DOF pose regression for LSD data and also a 6DOF pose regression for SSD data. The proposed approach performs far better than the naive approach, while storage and run-time overheads are almost negligible." @default.
• W3129297821 created "2021-03-01" @default.
• W3129297821 creator A5007109424 @default.
• W3129297821 creator A5048965393 @default.
• W3129297821 creator A5065056581 @default.
• W3129297821 date "2020-10-24" @default.
• W3129297821 modified "2023-10-18" @default.
• W3129297821 title "Learning to Switch CNNs with Model Agnostic Meta Learning for Fine Precision Visual Servoing" @default.
• W3129297821 cites W2082991751 @default.
• W3129297821 cites W2097117768 @default.
• W3129297821 cites W2108598243 @default.
• W3129297821 cites W2114347750 @default.
• W3129297821 cites W2141627350 @default.
• W3129297821 cites W2158782408 @default.
• W3129297821 cites W2162429410 @default.
• W3129297821 cites W2194775991 @default.
• W3129297821 cites W2200124539 @default.
• W3129297821 cites W2201912979 @default.
• W3129297821 cites W2296104201 @default.
• W3129297821 cites W2593800221 @default.
• W3129297821 cites W2605102758 @default.
• W3129297821 cites W2605111497 @default.
• W3129297821 cites W2609009256 @default.
• W3129297821 cites W2786808285 @default.
• W3129297821 cites W2788822937 @default.
• W3129297821 cites W2963527685 @default.
• W3129297821 cites W2964270628 @default.
• W3129297821 cites W2966233967 @default.
• W3129297821 cites W3003620461 @default.
• W3129297821 cites W3004010150 @default.
• W3129297821 doi "https://doi.org/10.1109/iros45743.2020.9341756" @default.
• W3129297821 hasPublicationYear "2020" @default.
• W3129297821 type Work @default.
• W3129297821 sameAs 3129297821 @default.
• W3129297821 citedByCount "3" @default.
• W3129297821 countsByYear W31292978212021 @default.
• W3129297821 countsByYear W31292978212022 @default.
• W3129297821 crossrefType "proceedings-article" @default.
• W3129297821 hasAuthorship W3129297821A5007109424 @default.
• W3129297821 hasAuthorship W3129297821A5048965393 @default.
• W3129297821 hasAuthorship W3129297821A5065056581 @default.
• W3129297821 hasBestOaLocation W31292978212 @default.
• W3129297821 hasConcept C107354338 @default.
• W3129297821 hasConcept C10912380 @default.
• W3129297821 hasConcept C111919701 @default.
• W3129297821 hasConcept C121332964 @default.
• W3129297821 hasConcept C153180895 @default.
• W3129297821 hasConcept C154945302 @default.
• W3129297821 hasConcept C2778755073 @default.
• W3129297821 hasConcept C2779960059 @default.
• W3129297821 hasConcept C31972630 @default.
• W3129297821 hasConcept C32731416 @default.
• W3129297821 hasConcept C41008148 @default.
• W3129297821 hasConcept C52102323 @default.
• W3129297821 hasConcept C62520636 @default.
• W3129297821 hasConcept C81363708 @default.
• W3129297821 hasConcept C90509273 @default.
• W3129297821 hasConceptScore W3129297821C107354338 @default.
• W3129297821 hasConceptScore W3129297821C10912380 @default.
• W3129297821 hasConceptScore W3129297821C111919701 @default.
• W3129297821 hasConceptScore W3129297821C121332964 @default.
• W3129297821 hasConceptScore W3129297821C153180895 @default.
• W3129297821 hasConceptScore W3129297821C154945302 @default.
• W3129297821 hasConceptScore W3129297821C2778755073 @default.
• W3129297821 hasConceptScore W3129297821C2779960059 @default.
• W3129297821 hasConceptScore W3129297821C31972630 @default.
• W3129297821 hasConceptScore W3129297821C32731416 @default.
• W3129297821 hasConceptScore W3129297821C41008148 @default.
• W3129297821 hasConceptScore W3129297821C52102323 @default.
• W3129297821 hasConceptScore W3129297821C62520636 @default.
• W3129297821 hasConceptScore W3129297821C81363708 @default.
• W3129297821 hasConceptScore W3129297821C90509273 @default.
• W3129297821 hasLocation W31292978211 @default.
• W3129297821 hasLocation W31292978212 @default.
• W3129297821 hasOpenAccess W3129297821 @default.
• W3129297821 hasPrimaryLocation W31292978211 @default.
• W3129297821 hasRelatedWork W165596340 @default.
• W3129297821 hasRelatedWork W1980647580 @default.
• W3129297821 hasRelatedWork W1982148096 @default.
• W3129297821 hasRelatedWork W2035976912 @default.
• W3129297821 hasRelatedWork W2101588601 @default.
• W3129297821 hasRelatedWork W2137020204 @default.
• W3129297821 hasRelatedWork W2331674254 @default.
• W3129297821 hasRelatedWork W2772917594 @default.
• W3129297821 hasRelatedWork W3034003528 @default.
• W3129297821 hasRelatedWork W4210409704 @default.
• W3129297821 isParatext "false" @default.
• W3129297821 isRetracted "false" @default.
• W3129297821 magId "3129297821" @default.
• W3129297821 workType "article" @default.