Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296153744> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4296153744 abstract "High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution representations. This will lose spatial information, and errors introduced by the decoder will be more serious when multiple types of objects are considered or objects are far away from the camera. To address these issues, we revisit the design paradigm of CNN for robotic perception tasks. We demonstrate that using parallel branches as opposed to serial stacked convolutional layers will be a more powerful design for robotic visual grasping tasks. In particular, guidelines of neural network design are provided for robotic perception tasks, e.g., high-resolution representation and lightweight design, which respond to the challenges in different manipulation scenarios. We then develop a novel grasping visual architecture referred to as HRG-Net, a parallel-branch structure that always maintains a high-resolution representation and repeatedly exchanges information across resolutions. Extensive experiments validate that these two designs can effectively enhance the accuracy of visual-based grasping and accelerate network training. We show a series of comparative experiments in real physical environments at Youtube: https://youtu.be/Jhlsp-xzHFY." @default.
- W4296153744 created "2022-09-17" @default.
- W4296153744 creator A5004258040 @default.
- W4296153744 creator A5015310258 @default.
- W4296153744 creator A5018344952 @default.
- W4296153744 creator A5038630321 @default.
- W4296153744 creator A5051737344 @default.
- W4296153744 date "2022-09-15" @default.
- W4296153744 modified "2023-09-24" @default.
- W4296153744 title "A Robotic Visual Grasping Design: Rethinking Convolution Neural Network with High-Resolutions" @default.
- W4296153744 doi "https://doi.org/10.48550/arxiv.2209.07459" @default.
- W4296153744 hasPublicationYear "2022" @default.
- W4296153744 type Work @default.
- W4296153744 citedByCount "0" @default.
- W4296153744 crossrefType "posted-content" @default.
- W4296153744 hasAuthorship W4296153744A5004258040 @default.
- W4296153744 hasAuthorship W4296153744A5015310258 @default.
- W4296153744 hasAuthorship W4296153744A5018344952 @default.
- W4296153744 hasAuthorship W4296153744A5038630321 @default.
- W4296153744 hasAuthorship W4296153744A5051737344 @default.
- W4296153744 hasBestOaLocation W42961537441 @default.
- W4296153744 hasConcept C104317684 @default.
- W4296153744 hasConcept C107457646 @default.
- W4296153744 hasConcept C154945302 @default.
- W4296153744 hasConcept C169760540 @default.
- W4296153744 hasConcept C17744445 @default.
- W4296153744 hasConcept C185592680 @default.
- W4296153744 hasConcept C199539241 @default.
- W4296153744 hasConcept C26760741 @default.
- W4296153744 hasConcept C2776359362 @default.
- W4296153744 hasConcept C31972630 @default.
- W4296153744 hasConcept C41008148 @default.
- W4296153744 hasConcept C45347329 @default.
- W4296153744 hasConcept C50644808 @default.
- W4296153744 hasConcept C55493867 @default.
- W4296153744 hasConcept C66746571 @default.
- W4296153744 hasConcept C81363708 @default.
- W4296153744 hasConcept C86803240 @default.
- W4296153744 hasConcept C94625758 @default.
- W4296153744 hasConceptScore W4296153744C104317684 @default.
- W4296153744 hasConceptScore W4296153744C107457646 @default.
- W4296153744 hasConceptScore W4296153744C154945302 @default.
- W4296153744 hasConceptScore W4296153744C169760540 @default.
- W4296153744 hasConceptScore W4296153744C17744445 @default.
- W4296153744 hasConceptScore W4296153744C185592680 @default.
- W4296153744 hasConceptScore W4296153744C199539241 @default.
- W4296153744 hasConceptScore W4296153744C26760741 @default.
- W4296153744 hasConceptScore W4296153744C2776359362 @default.
- W4296153744 hasConceptScore W4296153744C31972630 @default.
- W4296153744 hasConceptScore W4296153744C41008148 @default.
- W4296153744 hasConceptScore W4296153744C45347329 @default.
- W4296153744 hasConceptScore W4296153744C50644808 @default.
- W4296153744 hasConceptScore W4296153744C55493867 @default.
- W4296153744 hasConceptScore W4296153744C66746571 @default.
- W4296153744 hasConceptScore W4296153744C81363708 @default.
- W4296153744 hasConceptScore W4296153744C86803240 @default.
- W4296153744 hasConceptScore W4296153744C94625758 @default.
- W4296153744 hasLocation W42961537441 @default.
- W4296153744 hasOpenAccess W4296153744 @default.
- W4296153744 hasPrimaryLocation W42961537441 @default.
- W4296153744 hasRelatedWork W2529764055 @default.
- W4296153744 hasRelatedWork W2755240195 @default.
- W4296153744 hasRelatedWork W2766634277 @default.
- W4296153744 hasRelatedWork W2810384904 @default.
- W4296153744 hasRelatedWork W2897359454 @default.
- W4296153744 hasRelatedWork W2898938095 @default.
- W4296153744 hasRelatedWork W2980363492 @default.
- W4296153744 hasRelatedWork W3129634582 @default.
- W4296153744 hasRelatedWork W3176433844 @default.
- W4296153744 hasRelatedWork W4312417841 @default.
- W4296153744 isParatext "false" @default.
- W4296153744 isRetracted "false" @default.
- W4296153744 workType "article" @default.